Upload folder

.env

@@ -0,0 +1,9 @@
+OPENBLAS_NUM_THREADS = 1
+no_proxy = localhost, 127.0.0.1, ::1
+
+# You can change the location of the model, etc. by changing here
+weight_root = assets/weights
+weight_uvr5_root = assets/uvr5_weights
+index_root = logs
+outside_index_root = assets/indices
+rmvpe_root = assets/rmvpe

.github/PULL_REQUEST_TEMPLATE.md

@@ -0,0 +1,26 @@
+# Pull request checklist
+
+- [ ] The PR has a proper title. Use [Semantic Commit Messages](https://seesparkbox.com/foundry/semantic_commit_messages). (No more branch-name title please)
+- [ ] Make sure this is ready to be merged into the relevant branch. Please don't create a PR and let it hang for a few days.
+- [ ] Ensure you can run the codes you submitted succesfully. These submissions will be prioritized for review:
+
+    Introduce improvements in program execution speed;
+
+    Introduce improvements in synthesis quality;
+
+    Fix existing bugs reported by user feedback (or you met);
+
+    Introduce more convenient user operations.
+
+# PR type
+
+- Bug fix / new feature / synthesis quality improvement / program execution speed improvement
+
+# Description
+
+- Describe what this pull request is for.
+- What will it affect.
+
+# Screenshot
+
+- Please include a screenshot if applicable

.github/workflows/docker.yml

@@ -0,0 +1,70 @@
+name: Build and Push Docker Image
+
+on:
+  workflow_dispatch:
+  push:
+    # Sequence of patterns matched against refs/tags
+    tags:
+      - 'v*' # Push events to matching v*, i.e. v1.0, v20.15.10
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      packages: write
+      contents: read
+    steps:
+      - uses: actions/checkout@v3
+      - name: Set time zone
+        uses: szenius/set-timezone@v1.0
+        with:
+          timezoneLinux: "Asia/Shanghai"
+          timezoneMacos: "Asia/Shanghai"
+          timezoneWindows: "China Standard Time"
+
+      # # 如果有 dockerhub 账户，可以在github的secrets中配置下面两个，然后取消下面注释的这几行，并在meta步骤的images增加一行 ${{ github.repository }}
+      # - name: Login to DockerHub
+      #   uses: docker/login-action@v1
+      #   with:
+      #     username: ${{ secrets.DOCKERHUB_USERNAME }}
+      #     password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Login to GHCR
+        uses: docker/login-action@v2
+        with:
+          registry: ghcr.io
+          username: ${{ github.repository_owner }}
+          password: ${{ secrets.GITHUB_TOKEN }}
+
+      - name: Extract metadata (tags, labels) for Docker
+        id: meta
+        uses: docker/metadata-action@v4
+        with:
+          images: |
+            ghcr.io/${{ github.repository }}
+          # generate Docker tags based on the following events/attributes
+          #   nightly, master, pr-2, 1.2.3, 1.2, 1
+          tags: |
+            type=schedule,pattern=nightly
+            type=edge
+            type=ref,event=branch
+            type=ref,event=pr
+            type=semver,pattern={{version}}
+            type=semver,pattern={{major}}.{{minor}}
+            type=semver,pattern={{major}}
+
+      - name: Set up QEMU
+        uses: docker/setup-qemu-action@v2
+
+      - name: Set up Docker Buildx
+        uses: docker/setup-buildx-action@v2
+
+      - name: Build and push
+        id: docker_build
+        uses: docker/build-push-action@v4
+        with:
+          context: .
+          platforms: linux/amd64,linux/arm64
+          push: true
+          tags: ${{ steps.meta.outputs.tags }}
+          labels: ${{ steps.meta.outputs.labels }}

.github/workflows/genlocale.yml

@@ -0,0 +1,38 @@
+name: Generate and Sync Locale
+on:
+  push:
+    branches:
+      - main
+      - dev
+jobs:
+  genlocale:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@master
+
+      - name: Run locale generation
+        run: |
+          python3 i18n/scan_i18n.py
+          cd i18n
+          python3 locale_diff.py
+
+      - name: Commit back
+        if: ${{ !github.head_ref }}
+        id: commitback
+        continue-on-error: true
+        run: |
+          git config --local user.name 'github-actions[bot]'
+          git config --local user.email 'github-actions[bot]@users.noreply.github.com'
+          git add --all
+          git commit -m "chore(i18n): sync locale on ${{github.ref_name}}"
+
+      - name: Create Pull Request
+        if: steps.commitback.outcome == 'success'
+        continue-on-error: true
+        uses: peter-evans/create-pull-request@v5
+        with:
+          delete-branch: true
+          body: "Automatically sync i18n translation jsons"
+          title: "chore(i18n): sync locale on ${{github.ref_name}}"
+          commit-message: "chore(i18n): sync locale on ${{github.ref_name}}"
+          branch: genlocale-${{github.ref_name}}

.github/workflows/pull_format.yml

@@ -0,0 +1,48 @@
+name: Check Pull Format
+
+on:
+  pull_request_target:
+    types: [opened, reopened]
+
+jobs:
+  # This workflow closes invalid PR
+  close_pr:
+    # The type of runner that the job will run on
+    runs-on: ubuntu-latest
+    permissions: write-all
+
+    # Steps represent a sequence of tasks that will be executed as part of the job
+    steps:
+      - name: Close PR if it is not pointed to dev branch
+        if: github.event.pull_request.base.ref != 'dev'
+        uses: superbrothers/close-pull-request@v3
+        with:
+          # Optional. Post a issue comment just before closing a pull request.
+          comment: "Invalid PR to `non-dev` branch `${{ github.event.pull_request.base.ref }}`."
+
+  pull_format:
+    runs-on: ubuntu-latest
+    permissions:
+      contents: write
+
+    continue-on-error: true
+
+    steps:
+      - name: Checkout
+        continue-on-error: true
+        uses: actions/checkout@v3
+        with:
+          ref: ${{ github.head_ref }}
+          fetch-depth: 0
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Black
+        run: pip install "black[jupyter]"
+
+      - name: Run Black
+        # run: black $(git ls-files '*.py')
+        run: black .

.github/workflows/push_format.yml

@@ -0,0 +1,52 @@
+name: Standardize Code Format
+
+on:
+  push:
+    branches:
+      - main
+      - dev
+
+jobs:
+  push_format:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+      pull-requests: write
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: ${{github.ref_name}}
+
+      - name: Set up Python ${{ matrix.python-version }}
+        uses: actions/setup-python@v4
+        with:
+          python-version: ${{ matrix.python-version }}
+
+      - name: Install Black
+        run: pip install "black[jupyter]"
+
+      - name: Run Black
+        # run: black $(git ls-files '*.py')
+        run: black .
+
+      - name: Commit Back
+        continue-on-error: true
+        id: commitback
+        run: |
+          git config --local user.email "github-actions[bot]@users.noreply.github.com"
+          git config --local user.name "github-actions[bot]"
+          git add --all
+          git commit -m "chore(format): run black on ${{github.ref_name}}"
+
+      - name: Create Pull Request
+        if: steps.commitback.outcome == 'success'
+        continue-on-error: true
+        uses: peter-evans/create-pull-request@v5
+        with:
+          delete-branch: true
+          body: "Automatically apply code formatter change"
+          title: "chore(format): run black on ${{github.ref_name}}"
+          commit-message: "chore(format): run black on ${{github.ref_name}}"
+          branch: formatter-${{github.ref_name}}

.github/workflows/sync_dev.yml

@@ -0,0 +1,23 @@
+name: Merge dev into main
+
+on:
+  workflow_dispatch:
+
+jobs:
+  sync_dev:
+    runs-on: ubuntu-latest
+
+    permissions:
+      contents: write
+      pull-requests: write
+
+    steps:
+      - uses: actions/checkout@v3
+        with:
+          ref: main
+
+      - name: Create Pull Request
+        run: |
+          gh pr create --title "chore(sync): merge dev into main" --body "Merge dev to main" --base main --head dev
+        env:
+          GH_TOKEN: ${{ github.token }}

.github/workflows/unitest.yml

@@ -0,0 +1,36 @@
+name: Unit Test
+on: [ push, pull_request ]
+jobs:
+  build:
+    runs-on: ${{ matrix.os }}
+    strategy:
+      matrix:
+        python-version: ["3.8", "3.9", "3.10"]
+        os: [ubuntu-latest]
+      fail-fast: true
+
+    steps:
+    - uses: actions/checkout@master
+    - name: Set up Python ${{ matrix.python-version }}
+      uses: actions/setup-python@v4
+      with:
+        python-version: ${{ matrix.python-version }}
+    - name: Install dependencies
+      run: |
+        sudo apt update
+        sudo apt -y install ffmpeg
+        sudo apt -y install -qq aria2
+        aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d ./ -o hubert_base.pt
+        python -m pip install --upgrade pip
+        python -m pip install --upgrade setuptools
+        python -m pip install --upgrade wheel
+        pip install torch torchvision torchaudio
+        pip install -r requirements.txt
+    - name: Test step 1 & 2
+      run: |
+        mkdir -p logs/mi-test
+        touch logs/mi-test/preprocess.log
+        python infer/modules/train/preprocess.py logs/mute/0_gt_wavs 48000 8 logs/mi-test True 3.7
+        touch logs/mi-test/extract_f0_feature.log
+        python infer/modules/train/extract/extract_f0_print.py logs/mi-test $(nproc) pm
+        python infer/modules/train/extract_feature_print.py cpu 1 0 0 logs/mi-test v1 True

.gitignore

@@ -0,0 +1,28 @@
+.DS_Store
+__pycache__
+/TEMP
+*.pyd
+.venv
+/opt
+tools/aria2c/
+tools/flag.txt
+
+# Imported from huggingface.co/lj1995/VoiceConversionWebUI
+/pretrained
+/pretrained_v2
+/uvr5_weights
+hubert_base.pt
+rmvpe.onnx
+rmvpe.pt
+
+# Generated by RVC
+/logs
+/weights
+
+# To set a Python version for the project
+.tool-versions
+
+/runtime
+/assets/weights/*
+ffmpeg.*
+ffprobe.*

CONTRIBUTING.md

@@ -0,0 +1,11 @@
+# 贡献规则
+1. 一般来说，作者`@RVC-Boss`将拒绝所有的算法更改，除非它是为了修复某个代码层面的错误或警告
+2. 您可以贡献本仓库的其他位置，如翻译和WebUI，但请尽量作最小更改
+3. 所有更改都需要由`@RVC-Boss`批准，因此您的PR可能会被搁置
+4. 由此带来的不便请您谅解
+
+# Contributing Rules
+1. Generally, the author `@RVC-Boss` will reject all algorithm changes unless what is to fix a code-level error or warning.
+2. You can contribute to other parts of this repo like translations and WebUI, but please minimize your changes as much as possible.
+3. All changes need to be approved by `@RVC-Boss`, so your PR may be put on hold.
+4. Please accept our apologies for any inconvenience caused.

Dockerfile

@@ -0,0 +1,48 @@
+# syntax=docker/dockerfile:1
+
+FROM nvidia/cuda:11.6.2-cudnn8-runtime-ubuntu20.04
+
+EXPOSE 7865
+
+WORKDIR /app
+
+COPY . .
+
+# Install dependenceis to add PPAs
+RUN apt-get update && \
+    apt-get install -y -qq ffmpeg aria2 && apt clean && \
+    apt-get install -y software-properties-common && \
+    apt-get clean && \
+    rm -rf /var/lib/apt/lists/*
+
+# Add the deadsnakes PPA to get Python 3.9
+RUN add-apt-repository ppa:deadsnakes/ppa
+
+# Install Python 3.9 and pip
+RUN apt-get update && \
+    apt-get install -y build-essential python-dev python3-dev python3.9-distutils python3.9-dev python3.9 curl && \
+    apt-get clean && \
+    update-alternatives --install /usr/bin/python3 python3 /usr/bin/python3.9 1 && \
+    curl https://bootstrap.pypa.io/get-pip.py | python3.9
+
+# Set Python 3.9 as the default
+RUN update-alternatives --install /usr/bin/python python /usr/bin/python3.9 1
+
+RUN python3 -m pip install --upgrade pip==24.0
+RUN python3 -m pip install --no-cache-dir -r requirements.txt
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d assets/pretrained_v2/ -o D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d assets/pretrained_v2/ -o G40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d assets/pretrained_v2/ -o f0D40k.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d assets/pretrained_v2/ -o f0G40k.pth
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d assets/uvr5_weights/ -o HP2-人声vocals+非人声instrumentals.pth
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d assets/uvr5_weights/ -o HP5-主旋律人声vocals+其他instrumentals.pth
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d assets/hubert -o hubert_base.pt
+
+RUN aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d assets/rmvpe -o rmvpe.pt
+
+VOLUME [ "/app/weights", "/app/opt" ]
+
+CMD ["python3", "infer-web.py"]

LICENSE

@@ -0,0 +1,23 @@
+MIT License
+
+Copyright (c) 2023 liujing04
+Copyright (c) 2023 源文雨
+Copyright (c) 2023 Ftps
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

MIT协议暨相关引用库协议

@@ -0,0 +1,45 @@
+本软件及其相关代码以MIT协议开源，作者不对软件具备任何控制力，使用软件者、传播软件导出的声音者自负全责。
+如不认可该条款，则不能使用或引用软件包内任何代码和文件。
+
+特此授予任何获得本软件和相关文档文件（以下简称“软件”）副本的人免费使用、复制、修改、合并、出版、分发、再授权和/或销售本软件的权利，以及授予本软件所提供的人使用本软件的权利，但须符合以下条件：
+上述版权声明和本许可声明应包含在软件的所有副本或实质部分中。
+软件是“按原样”提供的，没有任何明示或暗示的保证，包括但不限于适销性、适用于特定目的和不侵权的保证。在任何情况下，作者或版权持有人均不承担因软件或软件的使用或其他交易而产生、产生或与之相关的任何索赔、损害赔偿或其他责任，无论是在合同诉讼、侵权诉讼还是其他诉讼中。
+
+
+The LICENCEs for related libraries are as follows.
+相关引用库协议如下：
+
+ContentVec
+https://github.com/auspicious3000/contentvec/blob/main/LICENSE
+MIT License
+
+VITS
+https://github.com/jaywalnut310/vits/blob/main/LICENSE
+MIT License
+
+HIFIGAN
+https://github.com/jik876/hifi-gan/blob/master/LICENSE
+MIT License
+
+gradio
+https://github.com/gradio-app/gradio/blob/main/LICENSE
+Apache License 2.0
+
+ffmpeg
+https://github.com/FFmpeg/FFmpeg/blob/master/COPYING.LGPLv3
+https://github.com/BtbN/FFmpeg-Builds/releases/download/autobuild-2021-02-28-12-32/ffmpeg-n4.3.2-160-gfbb9368226-win64-lgpl-4.3.zip
+LPGLv3 License
+MIT License
+
+ultimatevocalremovergui
+https://github.com/Anjok07/ultimatevocalremovergui/blob/master/LICENSE
+https://github.com/yang123qwe/vocal_separation_by_uvr5
+MIT License
+
+audio-slicer
+https://github.com/openvpi/audio-slicer/blob/main/LICENSE
+MIT License
+
+PySimpleGUI
+https://github.com/PySimpleGUI/PySimpleGUI/blob/master/license.txt
+LPGLv3 License

README.md

@@ -1,3 +1,14 @@
----
-license: mit
----
+<div align="center">
+
+<h1>easyGUI</h1>
+A fork of Retrieval based Voice Conversion WebUI <br><br>
+
+## Credits
++ [RVC](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI)
++ [ContentVec](https://github.com/auspicious3000/contentvec/)
++ [VITS](https://github.com/jaywalnut310/vits)
++ [HIFIGAN](https://github.com/jik876/hifi-gan)
++ [Gradio](https://github.com/gradio-app/gradio)
++ [FFmpeg](https://github.com/FFmpeg/FFmpeg)
++ [Vocal pitch extraction:RMVPE](https://github.com/Dream-High/RMVPE)
++ The pretrained model is trained and tested by [yxlllc](https://github.com/yxlllc/RMVPE) and [RVC-Boss](https://github.com/RVC-Boss).

Retrieval_based_Voice_Conversion_WebUI.ipynb

@@ -0,0 +1,403 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZFFCx5J80SGa"
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "GmFP6bN9dvOq"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 查看显卡\n",
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "jwu07JgqoFON"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 挂载谷歌云盘\n",
+    "\n",
+    "from google.colab import drive\n",
+    "\n",
+    "drive.mount(\"/content/drive\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "wjddIFr1oS3W"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 安装依赖\n",
+    "!apt-get -y install build-essential python3-dev ffmpeg\n",
+    "!pip3 install --upgrade setuptools wheel\n",
+    "!pip3 install --upgrade pip\n",
+    "!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ge_97mfpgqTm"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 克隆仓库\n",
+    "\n",
+    "!git clone --depth=1 -b stable https://github.com/fumiama/Retrieval-based-Voice-Conversion-WebUI\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "!mkdir -p pretrained uvr5_weights"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BLDEZADkvlw1"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 更新仓库（一般无需执行）\n",
+    "!git pull"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pqE0PrnuRqI2"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 安装aria2\n",
+    "!apt -y install -qq aria2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UG3XpUwEomUz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载底模\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HugjmZqZRuiF"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载人声分离模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2RCaT9FTR0ej"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载hubert_base\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @title #下载rmvpe模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Mwk7Q0Loqzjx"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘加载打包好的数据集到/content/dataset\n",
+    "\n",
+    "# @markdown 数据集位置\n",
+    "DATASET = (\n",
+    "    \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\"  # @param {type:\"string\"}\n",
+    ")\n",
+    "\n",
+    "!mkdir -p /content/dataset\n",
+    "!unzip -d /content/dataset -B {DATASET}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "PDlFxWHWEynD"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 重命名数据集中的重名文件\n",
+    "!ls -a /content/dataset/\n",
+    "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7vh6vphDwO0b"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 启动web\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "# %load_ext tensorboard\n",
+    "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+    "!python3 infer-web.py --colab --pycmd python3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "FgJuNeAwx5Y_"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动将训练后的模型文件备份到谷歌云盘\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "OVQoLQJXS7WX"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘恢复pth\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 7500  # @param {type:\"integer\"}\n",
+    "\n",
+    "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/*.index /content/\n",
+    "!cp /content/drive/MyDrive/*.npy /content/\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZKAyuKb9J6dz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动预处理（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 采样率\n",
+    "BITRATE = 48000  # @param {type:\"integer\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "CrxJqzAUKmPJ"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动提取特征（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "# @markdown 音高提取算法\n",
+    "ALGO = \"harvest\"  # @param {type:\"string\"}\n",
+    "\n",
+    "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+    "\n",
+    "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IMLPLKOaKj58"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动训练（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的GPU\n",
+    "USEGPU = \"0\"  # @param {type:\"string\"}\n",
+    "# @markdown 批大小\n",
+    "BATCHSIZE = 32  # @param {type:\"integer\"}\n",
+    "# @markdown 停止的epoch\n",
+    "MODELEPOCH = 3200  # @param {type:\"integer\"}\n",
+    "# @markdown 保存epoch间隔\n",
+    "EPOCHSAVE = 100  # @param {type:\"integer\"}\n",
+    "# @markdown 采样率\n",
+    "MODELSAMPLE = \"48k\"  # @param {type:\"string\"}\n",
+    "# @markdown 是否缓存训练集\n",
+    "CACHEDATA = 1  # @param {type:\"integer\"}\n",
+    "# @markdown 是否仅保存最新的ckpt文件\n",
+    "ONLYLATEST = 0  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "haYA81hySuDl"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "QhSiPTVPoIRh"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "private_outputs": true,
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

Retrieval_based_Voice_Conversion_WebUI_v2.ipynb

@@ -0,0 +1,422 @@
+{
+ "cells": [
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "# [Retrieval-based-Voice-Conversion-WebUI](https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI) Training notebook"
+   ]
+  },
+  {
+   "attachments": {},
+   "cell_type": "markdown",
+   "metadata": {
+    "id": "ZFFCx5J80SGa"
+   },
+   "source": [
+    "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/RVC-Project/Retrieval-based-Voice-Conversion-WebUI/blob/main/Retrieval_based_Voice_Conversion_WebUI_v2.ipynb)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "GmFP6bN9dvOq"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #查看显卡\n",
+    "!nvidia-smi"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "jwu07JgqoFON"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 挂载谷歌云盘\n",
+    "\n",
+    "from google.colab import drive\n",
+    "\n",
+    "drive.mount(\"/content/drive\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "wjddIFr1oS3W"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #安装依赖\n",
+    "!apt-get -y install build-essential python3-dev ffmpeg\n",
+    "!pip3 install --upgrade setuptools wheel\n",
+    "!pip3 install --upgrade pip\n",
+    "!pip3 install faiss-cpu==1.7.2 fairseq gradio==3.14.0 ffmpeg ffmpeg-python praat-parselmouth pyworld numpy==1.23.5 numba==0.56.4 librosa==0.9.2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ge_97mfpgqTm"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #克隆仓库\n",
+    "\n",
+    "!mkdir Retrieval-based-Voice-Conversion-WebUI\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "!git init\n",
+    "!git remote add origin https://github.com/RVC-Project/Retrieval-based-Voice-Conversion-WebUI.git\n",
+    "!git fetch origin cfd984812804ddc9247d65b14c82cd32e56c1133 --depth=1\n",
+    "!git reset --hard FETCH_HEAD"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "BLDEZADkvlw1"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #更新仓库（一般无需执行）\n",
+    "!git pull"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "pqE0PrnuRqI2"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #安装aria2\n",
+    "!apt -y install -qq aria2"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "UG3XpUwEomUz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 下载底模\n",
+    "\n",
+    "# v1\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o G48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0D48k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G40k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained -o f0G48k.pth\n",
+    "\n",
+    "# v2\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o D48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o G48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0D48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0D48k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G32k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G32k.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G40k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G40k.pth\n",
+    "# !aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/pretrained_v2/f0G48k.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/pretrained_v2 -o f0G48k.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "HugjmZqZRuiF"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #下载人声分离模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP2-人声vocals+非人声instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP2-人声vocals+非人声instrumentals.pth\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/uvr5_weights/HP5-主旋律人声vocals+其他instrumentals.pth -d /content/Retrieval-based-Voice-Conversion-WebUI/uvr5_weights -o HP5-主旋律人声vocals+其他instrumentals.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "2RCaT9FTR0ej"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #下载hubert_base\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/hubert_base.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o hubert_base.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# @title #下载rmvpe模型\n",
+    "!aria2c --console-log-level=error -c -x 16 -s 16 -k 1M https://huggingface.co/lj1995/VoiceConversionWebUI/resolve/main/rmvpe.pt -d /content/Retrieval-based-Voice-Conversion-WebUI -o rmvpe.pt"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "Mwk7Q0Loqzjx"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #从谷歌云盘加载打包好的数据集到/content/dataset\n",
+    "\n",
+    "# @markdown 数据集位置\n",
+    "DATASET = (\n",
+    "    \"/content/drive/MyDrive/dataset/lulu20230327_32k.zip\"  # @param {type:\"string\"}\n",
+    ")\n",
+    "\n",
+    "!mkdir -p /content/dataset\n",
+    "!unzip -d /content/dataset -B {DATASET}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "PDlFxWHWEynD"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #重命名数据集中的重名文件\n",
+    "!ls -a /content/dataset/\n",
+    "!rename 's/(\\w+)\\.(\\w+)~(\\d*)/$1_$3.$2/' /content/dataset/*.*~*"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "7vh6vphDwO0b"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #启动webui\n",
+    "%cd /content/Retrieval-based-Voice-Conversion-WebUI\n",
+    "# %load_ext tensorboard\n",
+    "# %tensorboard --logdir /content/Retrieval-based-Voice-Conversion-WebUI/logs\n",
+    "!python3 infer-web.py --colab --pycmd python3"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "FgJuNeAwx5Y_"
+   },
+   "outputs": [],
+   "source": [
+    "# @title #手动将训练后的模型文件备份到谷歌云盘\n",
+    "# @markdown #需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown #模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown #模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/added_*.index /content/drive/MyDrive/\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/total_*.npy /content/drive/MyDrive/\n",
+    "\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "OVQoLQJXS7WX"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 从谷歌云盘恢复pth\n",
+    "# @markdown 需要自己查看logs文件夹下模型的文件名，手动修改下方命令末尾的文件名\n",
+    "\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 模型epoch\n",
+    "MODELEPOCH = 7500  # @param {type:\"integer\"}\n",
+    "\n",
+    "!mkdir -p /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "!cp /content/drive/MyDrive/*.index /content/\n",
+    "!cp /content/drive/MyDrive/*.npy /content/\n",
+    "!cp /content/drive/MyDrive/{MODELNAME}{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/weights/{MODELNAME}.pth"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "ZKAyuKb9J6dz"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动预处理（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 采样率\n",
+    "BITRATE = 48000  # @param {type:\"integer\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 trainset_preprocess_pipeline_print.py /content/dataset {BITRATE} {THREADCOUNT} logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "CrxJqzAUKmPJ"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动提取特征（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的进程数\n",
+    "THREADCOUNT = 8  # @param {type:\"integer\"}\n",
+    "# @markdown 音高提取算法\n",
+    "ALGO = \"harvest\"  # @param {type:\"string\"}\n",
+    "\n",
+    "!python3 extract_f0_print.py logs/{MODELNAME} {THREADCOUNT} {ALGO}\n",
+    "\n",
+    "!python3 extract_feature_print.py cpu 1 0 0 logs/{MODELNAME} True"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "IMLPLKOaKj58"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 手动训练（不推荐）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 使用的GPU\n",
+    "USEGPU = \"0\"  # @param {type:\"string\"}\n",
+    "# @markdown 批大小\n",
+    "BATCHSIZE = 32  # @param {type:\"integer\"}\n",
+    "# @markdown 停止的epoch\n",
+    "MODELEPOCH = 3200  # @param {type:\"integer\"}\n",
+    "# @markdown 保存epoch间隔\n",
+    "EPOCHSAVE = 100  # @param {type:\"integer\"}\n",
+    "# @markdown 采样率\n",
+    "MODELSAMPLE = \"48k\"  # @param {type:\"string\"}\n",
+    "# @markdown 是否缓存训练集\n",
+    "CACHEDATA = 1  # @param {type:\"integer\"}\n",
+    "# @markdown 是否仅保存最新的ckpt文件\n",
+    "ONLYLATEST = 0  # @param {type:\"integer\"}\n",
+    "\n",
+    "!python3 train_nsf_sim_cache_sid_load_pretrain.py -e lulu -sr {MODELSAMPLE} -f0 1 -bs {BATCHSIZE} -g {USEGPU} -te {MODELEPOCH} -se {EPOCHSAVE} -pg pretrained/f0G{MODELSAMPLE}.pth -pd pretrained/f0D{MODELSAMPLE}.pth -l {ONLYLATEST} -c {CACHEDATA}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "haYA81hySuDl"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 删除其它pth，只留选中的（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*.pth\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "id": "QhSiPTVPoIRh"
+   },
+   "outputs": [],
+   "source": [
+    "# @title 清除项目下所有文件，只留选中的模型（慎点，仔细看代码）\n",
+    "# @markdown 模型名\n",
+    "MODELNAME = \"lulu\"  # @param {type:\"string\"}\n",
+    "# @markdown 选中模型epoch\n",
+    "MODELEPOCH = 9600  # @param {type:\"integer\"}\n",
+    "\n",
+    "!echo \"备份选中的模型。。。\"\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth /content/{MODELNAME}_D_{MODELEPOCH}.pth\n",
+    "!cp /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth /content/{MODELNAME}_G_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"正在删除。。。\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}\n",
+    "!rm -rf /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/*\n",
+    "\n",
+    "!echo \"恢复选中的模型。。。\"\n",
+    "!mv /content/{MODELNAME}_D_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/G_{MODELEPOCH}.pth\n",
+    "!mv /content/{MODELNAME}_G_{MODELEPOCH}.pth /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}/D_{MODELEPOCH}.pth\n",
+    "\n",
+    "!echo \"删除完成\"\n",
+    "!ls /content/Retrieval-based-Voice-Conversion-WebUI/logs/{MODELNAME}"
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "private_outputs": true,
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "Python 3",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}

api_231006.py

@@ -0,0 +1,440 @@
+#api for 231006 release version by Xiaokai
+import os
+import sys
+import json
+import re
+import time
+import librosa
+import torch
+import numpy as np
+import torch.nn.functional as F
+import torchaudio.transforms as tat
+import sounddevice as sd
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import threading
+import uvicorn
+import logging
+
+# Initialize the logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Define FastAPI app
+app = FastAPI()
+
+class GUIConfig:
+    def __init__(self) -> None:
+        self.pth_path: str = ""
+        self.index_path: str = ""
+        self.pitch: int = 0
+        self.samplerate: int = 40000
+        self.block_time: float = 1.0  # s
+        self.buffer_num: int = 1
+        self.threhold: int = -60
+        self.crossfade_time: float = 0.05
+        self.extra_time: float = 2.5
+        self.I_noise_reduce = False
+        self.O_noise_reduce = False
+        self.rms_mix_rate = 0.0
+        self.index_rate = 0.3
+        self.f0method = "rmvpe"
+        self.sg_input_device = ""
+        self.sg_output_device = ""
+
+class ConfigData(BaseModel):
+    pth_path: str
+    index_path: str
+    sg_input_device: str
+    sg_output_device: str
+    threhold: int = -60
+    pitch: int = 0
+    index_rate: float = 0.3
+    rms_mix_rate: float = 0.0
+    block_time: float = 0.25
+    crossfade_length: float = 0.05
+    extra_time: float = 2.5
+    n_cpu: int = 4
+    I_noise_reduce: bool = False
+    O_noise_reduce: bool = False
+
+class AudioAPI:
+    def __init__(self) -> None:
+        self.gui_config = GUIConfig()
+        self.config = None  # Initialize Config object as None
+        self.flag_vc = False
+        self.function = "vc"
+        self.delay_time = 0
+        self.rvc = None  # Initialize RVC object as None
+
+    def load(self):
+        input_devices, output_devices, _, _ = self.get_devices()
+        try:
+            with open("configs/config.json", "r", encoding='utf-8') as j:
+                data = json.load(j)
+                data["rmvpe"] = True  # Ensure rmvpe is the only f0method
+                if data["sg_input_device"] not in input_devices:
+                    data["sg_input_device"] = input_devices[sd.default.device[0]]
+                if data["sg_output_device"] not in output_devices:
+                    data["sg_output_device"] = output_devices[sd.default.device[1]]
+        except Exception as e:
+            logger.error(f"Failed to load configuration: {e}")
+            with open("configs/config.json", "w", encoding='utf-8') as j:
+                data = {
+                    "pth_path": " ",
+                    "index_path": " ",
+                    "sg_input_device": input_devices[sd.default.device[0]],
+                    "sg_output_device": output_devices[sd.default.device[1]],
+                    "threhold": "-60",
+                    "pitch": "0",
+                    "index_rate": "0",
+                    "rms_mix_rate": "0",
+                    "block_time": "0.25",
+                    "crossfade_length": "0.05",
+                    "extra_time": "2.5",
+                    "f0method": "rmvpe",
+                    "use_jit": False,
+                }
+                data["rmvpe"] = True  # Ensure rmvpe is the only f0method
+                json.dump(data, j, ensure_ascii=False)
+        return data
+
+    def set_values(self, values):
+        logger.info(f"Setting values: {values}")
+        if not values.pth_path.strip():
+            raise HTTPException(status_code=400, detail="Please select a .pth file")
+        if not values.index_path.strip():
+            raise HTTPException(status_code=400, detail="Please select an index file")
+        self.set_devices(values.sg_input_device, values.sg_output_device)
+        self.config.use_jit = False
+        self.gui_config.pth_path = values.pth_path
+        self.gui_config.index_path = values.index_path
+        self.gui_config.threhold = values.threhold
+        self.gui_config.pitch = values.pitch
+        self.gui_config.block_time = values.block_time
+        self.gui_config.crossfade_time = values.crossfade_length
+        self.gui_config.extra_time = values.extra_time
+        self.gui_config.I_noise_reduce = values.I_noise_reduce
+        self.gui_config.O_noise_reduce = values.O_noise_reduce
+        self.gui_config.rms_mix_rate = values.rms_mix_rate
+        self.gui_config.index_rate = values.index_rate
+        self.gui_config.n_cpu = values.n_cpu
+        self.gui_config.f0method = "rmvpe"
+        return True
+
+    def start_vc(self):
+        torch.cuda.empty_cache()
+        self.flag_vc = True
+        self.rvc = rvc_for_realtime.RVC(
+            self.gui_config.pitch,
+            self.gui_config.pth_path,
+            self.gui_config.index_path,
+            self.gui_config.index_rate,
+            0,
+            0,
+            0,
+            self.config,
+            self.rvc if self.rvc else None,
+        )
+        self.gui_config.samplerate = self.rvc.tgt_sr
+        self.zc = self.rvc.tgt_sr // 100
+        self.block_frame = (
+            int(
+                np.round(
+                    self.gui_config.block_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.block_frame_16k = 160 * self.block_frame // self.zc
+        self.crossfade_frame = (
+            int(
+                np.round(
+                    self.gui_config.crossfade_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.sola_search_frame = self.zc
+        self.extra_frame = (
+            int(
+                np.round(
+                    self.gui_config.extra_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.input_wav = torch.zeros(
+            self.extra_frame + self.crossfade_frame + self.sola_search_frame + self.block_frame,
+            device=self.config.device,
+            dtype=torch.float32,
+        )
+        self.input_wav_res = torch.zeros(
+            160 * self.input_wav.shape[0] // self.zc,
+            device=self.config.device,
+            dtype=torch.float32,
+        )
+        self.pitch = np.zeros(self.input_wav.shape[0] // self.zc, dtype="int32")
+        self.pitchf = np.zeros(self.input_wav.shape[0] // self.zc, dtype="float64")
+        self.sola_buffer = torch.zeros(self.crossfade_frame, device=self.config.device, dtype=torch.float32)
+        self.nr_buffer = self.sola_buffer.clone()
+        self.output_buffer = self.input_wav.clone()
+        self.res_buffer = torch.zeros(2 * self.zc, device=self.config.device, dtype=torch.float32)
+        self.valid_rate = 1 - (self.extra_frame - 1) / self.input_wav.shape[0]
+        self.fade_in_window = (
+            torch.sin(0.5 * np.pi * torch.linspace(0.0, 1.0, steps=self.crossfade_frame, device=self.config.device, dtype=torch.float32)) ** 2
+        )
+        self.fade_out_window = 1 - self.fade_in_window
+        self.resampler = tat.Resample(
+            orig_freq=self.gui_config.samplerate,
+            new_freq=16000,
+            dtype=torch.float32,
+        ).to(self.config.device)
+        self.tg = TorchGate(
+            sr=self.gui_config.samplerate, n_fft=4 * self.zc, prop_decrease=0.9
+        ).to(self.config.device)
+        thread_vc = threading.Thread(target=self.soundinput)
+        thread_vc.start()
+
+    def soundinput(self):
+        channels = 1 if sys.platform == "darwin" else 2
+        with sd.Stream(
+            channels=channels,
+            callback=self.audio_callback,
+            blocksize=self.block_frame,
+            samplerate=self.gui_config.samplerate,
+            dtype="float32",
+        ) as stream:
+            global stream_latency
+            stream_latency = stream.latency[-1]
+            while self.flag_vc:
+                time.sleep(self.gui_config.block_time)
+                logger.info("Audio block passed.")
+        logger.info("Ending VC")
+
+    def audio_callback(self, indata: np.ndarray, outdata: np.ndarray, frames, times, status):
+        start_time = time.perf_counter()
+        indata = librosa.to_mono(indata.T)
+        if self.gui_config.threhold > -60:
+            rms = librosa.feature.rms(y=indata, frame_length=4 * self.zc, hop_length=self.zc)
+            db_threhold = (librosa.amplitude_to_db(rms, ref=1.0)[0] < self.gui_config.threhold)
+            for i in range(db_threhold.shape[0]):
+                if db_threhold[i]:
+                    indata[i * self.zc : (i + 1) * self.zc] = 0
+        self.input_wav[: -self.block_frame] = self.input_wav[self.block_frame :].clone()
+        self.input_wav[-self.block_frame :] = torch.from_numpy(indata).to(self.config.device)
+        self.input_wav_res[: -self.block_frame_16k] = self.input_wav_res[self.block_frame_16k :].clone()
+        if self.gui_config.I_noise_reduce and self.function == "vc":
+            input_wav = self.input_wav[-self.crossfade_frame - self.block_frame - 2 * self.zc :]
+            input_wav = self.tg(input_wav.unsqueeze(0), self.input_wav.unsqueeze(0))[0, 2 * self.zc :]
+            input_wav[: self.crossfade_frame] *= self.fade_in_window
+            input_wav[: self.crossfade_frame] += self.nr_buffer * self.fade_out_window
+            self.nr_buffer[:] = input_wav[-self.crossfade_frame :]
+            input_wav = torch.cat((self.res_buffer[:], input_wav[: self.block_frame]))
+            self.res_buffer[:] = input_wav[-2 * self.zc :]
+            self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(input_wav)[160:]
+        else:
+            self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(self.input_wav[-self.block_frame - 2 * self.zc :])[160:]
+        if self.function == "vc":
+            f0_extractor_frame = self.block_frame_16k + 800
+            if self.gui_config.f0method == "rmvpe":
+                f0_extractor_frame = (5120 * ((f0_extractor_frame - 1) // 5120 + 1) - 160)
+            infer_wav = self.rvc.infer(
+                self.input_wav_res,
+                self.input_wav_res[-f0_extractor_frame:].cpu().numpy(),
+                self.block_frame_16k,
+                self.valid_rate,
+                self.pitch,
+                self.pitchf,
+                self.gui_config.f0method,
+            )
+            infer_wav = infer_wav[-self.crossfade_frame - self.sola_search_frame - self.block_frame :]
+        else:
+            infer_wav = self.input_wav[-self.crossfade_frame - self.sola_search_frame - self.block_frame :].clone()
+        if (self.gui_config.O_noise_reduce and self.function == "vc") or (self.gui_config.I_noise_reduce and self.function == "im"):
+            self.output_buffer[: -self.block_frame] = self.output_buffer[self.block_frame :].clone()
+            self.output_buffer[-self.block_frame :] = infer_wav[-self.block_frame :]
+            infer_wav = self.tg(infer_wav.unsqueeze(0), self.output_buffer.unsqueeze(0)).squeeze(0)
+        if self.gui_config.rms_mix_rate < 1 and self.function == "vc":
+            rms1 = librosa.feature.rms(y=self.input_wav_res[-160 * infer_wav.shape[0] // self.zc :].cpu().numpy(), frame_length=640, hop_length=160)
+            rms1 = torch.from_numpy(rms1).to(self.config.device)
+            rms1 = F.interpolate(rms1.unsqueeze(0), size=infer_wav.shape[0] + 1, mode="linear", align_corners=True)[0, 0, :-1]
+            rms2 = librosa.feature.rms(y=infer_wav[:].cpu().numpy(), frame_length=4 * self.zc, hop_length=self.zc)
+            rms2 = torch.from_numpy(rms2).to(self.config.device)
+            rms2 = F.interpolate(rms2.unsqueeze(0), size=infer_wav.shape[0] + 1, mode="linear", align_corners=True)[0, 0, :-1]
+            rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-3)
+            infer_wav *= torch.pow(rms1 / rms2, torch.tensor(1 - self.gui_config.rms_mix_rate))
+        conv_input = infer_wav[None, None, : self.crossfade_frame + self.sola_search_frame]
+        cor_nom = F.conv1d(conv_input, self.sola_buffer[None, None, :])
+        cor_den = torch.sqrt(F.conv1d(conv_input**2, torch.ones(1, 1, self.crossfade_frame, device=self.config.device)) + 1e-8)
+        if sys.platform == "darwin":
+            _, sola_offset = torch.max(cor_nom[0, 0] / cor_den[0, 0])
+            sola_offset = sola_offset.item()
+        else:
+            sola_offset = torch.argmax(cor_nom[0, 0] / cor_den[0, 0])
+        logger.info(f"sola_offset = {sola_offset}")
+        infer_wav = infer_wav[sola_offset : sola_offset + self.block_frame + self.crossfade_frame]
+        infer_wav[: self.crossfade_frame] *= self.fade_in_window
+        infer_wav[: self.crossfade_frame] += self.sola_buffer * self.fade_out_window
+        self.sola_buffer[:] = infer_wav[-self.crossfade_frame :]
+        if sys.platform == "darwin":
+            outdata[:] = infer_wav[: -self.crossfade_frame].cpu().numpy()[:, np.newaxis]
+        else:
+            outdata[:] = infer_wav[: -self.crossfade_frame].repeat(2, 1).t().cpu().numpy()
+        total_time = time.perf_counter() - start_time
+        logger.info(f"Infer time: {total_time:.2f}")
+
+    def get_devices(self, update: bool = True):
+        if update:
+            sd._terminate()
+            sd._initialize()
+        devices = sd.query_devices()
+        hostapis = sd.query_hostapis()
+        for hostapi in hostapis:
+            for device_idx in hostapi["devices"]:
+                devices[device_idx]["hostapi_name"] = hostapi["name"]
+        input_devices = [
+            f"{d['name']} ({d['hostapi_name']})"
+            for d in devices
+            if d["max_input_channels"] > 0
+        ]
+        output_devices = [
+            f"{d['name']} ({d['hostapi_name']})"
+            for d in devices
+            if d["max_output_channels"] > 0
+        ]
+        input_devices_indices = [
+            d["index"] if "index" in d else d["name"]
+            for d in devices
+            if d["max_input_channels"] > 0
+        ]
+        output_devices_indices = [
+            d["index"] if "index" in d else d["name"]
+            for d in devices
+            if d["max_output_channels"] > 0
+        ]
+        return (
+            input_devices,
+            output_devices,
+            input_devices_indices,
+            output_devices_indices,
+        )
+
+    def set_devices(self, input_device, output_device):
+        (
+            input_devices,
+            output_devices,
+            input_device_indices,
+            output_device_indices,
+        ) = self.get_devices()
+        logger.debug(f"Available input devices: {input_devices}")
+        logger.debug(f"Available output devices: {output_devices}")
+        logger.debug(f"Selected input device: {input_device}")
+        logger.debug(f"Selected output device: {output_device}")
+
+        if input_device not in input_devices:
+            logger.error(f"Input device '{input_device}' is not in the list of available devices")
+            raise HTTPException(status_code=400, detail=f"Input device '{input_device}' is not available")
+        
+        if output_device not in output_devices:
+            logger.error(f"Output device '{output_device}' is not in the list of available devices")
+            raise HTTPException(status_code=400, detail=f"Output device '{output_device}' is not available")
+
+        sd.default.device[0] = input_device_indices[input_devices.index(input_device)]
+        sd.default.device[1] = output_device_indices[output_devices.index(output_device)]
+        logger.info(f"Input device set to {sd.default.device[0]}: {input_device}")
+        logger.info(f"Output device set to {sd.default.device[1]}: {output_device}")
+
+audio_api = AudioAPI()
+
+@app.get("/inputDevices", response_model=list)
+def get_input_devices():
+    try:
+        input_devices, _, _, _ = audio_api.get_devices()
+        return input_devices
+    except Exception as e:
+        logger.error(f"Failed to get input devices: {e}")
+        raise HTTPException(status_code=500, detail="Failed to get input devices")
+
+@app.get("/outputDevices", response_model=list)
+def get_output_devices():
+    try:
+        _, output_devices, _, _ = audio_api.get_devices()
+        return output_devices
+    except Exception as e:
+        logger.error(f"Failed to get output devices: {e}")
+        raise HTTPException(status_code=500, detail="Failed to get output devices")
+
+@app.post("/config")
+def configure_audio(config_data: ConfigData):
+    try:
+        logger.info(f"Configuring audio with data: {config_data}")
+        if audio_api.set_values(config_data):
+            settings = config_data.dict()
+            settings["use_jit"] = False
+            settings["f0method"] = "rmvpe"
+            with open("configs/config.json", "w", encoding='utf-8') as j:
+                json.dump(settings, j, ensure_ascii=False)
+            logger.info("Configuration set successfully")
+            return {"message": "Configuration set successfully"}
+    except HTTPException as e:
+        logger.error(f"Configuration error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Configuration failed: {e}")
+        raise HTTPException(status_code=400, detail=f"Configuration failed: {e}")
+
+@app.post("/start")
+def start_conversion():
+    try:
+        if not audio_api.flag_vc:
+            audio_api.start_vc()
+            return {"message": "Audio conversion started"}
+        else:
+            logger.warning("Audio conversion already running")
+            raise HTTPException(status_code=400, detail="Audio conversion already running")
+    except HTTPException as e:
+        logger.error(f"Start conversion error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Failed to start conversion: {e}")
+        raise HTTPException(status_code=500, detail=f"Failed to start conversion: {e}")
+
+@app.post("/stop")
+def stop_conversion():
+    try:
+        if audio_api.flag_vc:
+            audio_api.flag_vc = False
+            global stream_latency
+            stream_latency = -1
+            return {"message": "Audio conversion stopped"}
+        else:
+            logger.warning("Audio conversion not running")
+            raise HTTPException(status_code=400, detail="Audio conversion not running")
+    except HTTPException as e:
+        logger.error(f"Stop conversion error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Failed to stop conversion: {e}")
+        raise HTTPException(status_code=500, detail=f"Failed to stop conversion: {e}")
+
+if __name__ == "__main__":
+    if sys.platform == "win32":
+        from multiprocessing import freeze_support
+        freeze_support()
+    load_dotenv()
+    os.environ["OMP_NUM_THREADS"] = "4"
+    if sys.platform == "darwin":
+        os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
+    from tools.torchgate import TorchGate
+    import tools.rvc_for_realtime as rvc_for_realtime
+    from configs.config import Config
+    audio_api.config = Config()
+    uvicorn.run(app, host="0.0.0.0", port=6242)

api_240604.py

@@ -0,0 +1,565 @@
+#api for 240604 release version by Xiaokai
+import os
+import sys
+import json
+import re
+import time
+import librosa
+import torch
+import numpy as np
+import torch.nn.functional as F
+import torchaudio.transforms as tat
+import sounddevice as sd
+from dotenv import load_dotenv
+from fastapi import FastAPI, HTTPException
+from pydantic import BaseModel
+import threading
+import uvicorn
+import logging
+from multiprocessing import Queue, Process, cpu_count, freeze_support
+
+# Initialize the logger
+logging.basicConfig(level=logging.INFO)
+logger = logging.getLogger(__name__)
+
+# Define FastAPI app
+app = FastAPI()
+
+class GUIConfig:
+    def __init__(self) -> None:
+        self.pth_path: str = ""
+        self.index_path: str = ""
+        self.pitch: int = 0
+        self.formant: float = 0.0
+        self.sr_type: str = "sr_model"
+        self.block_time: float = 0.25  # s
+        self.threhold: int = -60
+        self.crossfade_time: float = 0.05
+        self.extra_time: float = 2.5
+        self.I_noise_reduce: bool = False
+        self.O_noise_reduce: bool = False
+        self.use_pv: bool = False
+        self.rms_mix_rate: float = 0.0
+        self.index_rate: float = 0.0
+        self.n_cpu: int = 4
+        self.f0method: str = "fcpe"
+        self.sg_input_device: str = ""
+        self.sg_output_device: str = ""
+
+class ConfigData(BaseModel):
+    pth_path: str
+    index_path: str
+    sg_input_device: str
+    sg_output_device: str
+    threhold: int = -60
+    pitch: int = 0
+    formant: float = 0.0
+    index_rate: float = 0.3
+    rms_mix_rate: float = 0.0
+    block_time: float = 0.25
+    crossfade_length: float = 0.05
+    extra_time: float = 2.5
+    n_cpu: int = 4
+    I_noise_reduce: bool = False
+    O_noise_reduce: bool = False
+    use_pv: bool = False
+    f0method: str = "fcpe"
+
+class Harvest(Process):
+    def __init__(self, inp_q, opt_q):
+        super(Harvest, self).__init__()
+        self.inp_q = inp_q
+        self.opt_q = opt_q
+
+    def run(self):
+        import numpy as np
+        import pyworld
+        while True:
+            idx, x, res_f0, n_cpu, ts = self.inp_q.get()
+            f0, t = pyworld.harvest(
+                x.astype(np.double),
+                fs=16000,
+                f0_ceil=1100,
+                f0_floor=50,
+                frame_period=10,
+            )
+            res_f0[idx] = f0
+            if len(res_f0.keys()) >= n_cpu:
+                self.opt_q.put(ts)
+
+class AudioAPI:
+    def __init__(self) -> None:
+        self.gui_config = GUIConfig()
+        self.config = None  # Initialize Config object as None
+        self.flag_vc = False
+        self.function = "vc"
+        self.delay_time = 0
+        self.rvc = None  # Initialize RVC object as None
+        self.inp_q = None
+        self.opt_q = None
+        self.n_cpu = min(cpu_count(), 8)
+
+    def initialize_queues(self):
+        self.inp_q = Queue()
+        self.opt_q = Queue()
+        for _ in range(self.n_cpu):
+            p = Harvest(self.inp_q, self.opt_q)
+            p.daemon = True
+            p.start()
+
+    def load(self):
+        input_devices, output_devices, _, _ = self.get_devices()
+        try:
+            with open("configs/config.json", "r", encoding='utf-8') as j:
+                data = json.load(j)
+                if data["sg_input_device"] not in input_devices:
+                    data["sg_input_device"] = input_devices[sd.default.device[0]]
+                if data["sg_output_device"] not in output_devices:
+                    data["sg_output_device"] = output_devices[sd.default.device[1]]
+        except Exception as e:
+            logger.error(f"Failed to load configuration: {e}")
+            with open("configs/config.json", "w", encoding='utf-8') as j:
+                data = {
+                    "pth_path": "",
+                    "index_path": "",
+                    "sg_input_device": input_devices[sd.default.device[0]],
+                    "sg_output_device": output_devices[sd.default.device[1]],
+                    "threhold": -60,
+                    "pitch": 0,
+                    "formant": 0.0,
+                    "index_rate": 0,
+                    "rms_mix_rate": 0,
+                    "block_time": 0.25,
+                    "crossfade_length": 0.05,
+                    "extra_time": 2.5,
+                    "n_cpu": 4,
+                    "f0method": "fcpe",
+                    "use_jit": False,
+                    "use_pv": False,
+                }
+                json.dump(data, j, ensure_ascii=False)
+        return data
+
+    def set_values(self, values):
+        logger.info(f"Setting values: {values}")
+        if not values.pth_path.strip():
+            raise HTTPException(status_code=400, detail="Please select a .pth file")
+        if not values.index_path.strip():
+            raise HTTPException(status_code=400, detail="Please select an index file")
+        self.set_devices(values.sg_input_device, values.sg_output_device)
+        self.config.use_jit = False
+        self.gui_config.pth_path = values.pth_path
+        self.gui_config.index_path = values.index_path
+        self.gui_config.threhold = values.threhold
+        self.gui_config.pitch = values.pitch
+        self.gui_config.formant = values.formant
+        self.gui_config.block_time = values.block_time
+        self.gui_config.crossfade_time = values.crossfade_length
+        self.gui_config.extra_time = values.extra_time
+        self.gui_config.I_noise_reduce = values.I_noise_reduce
+        self.gui_config.O_noise_reduce = values.O_noise_reduce
+        self.gui_config.rms_mix_rate = values.rms_mix_rate
+        self.gui_config.index_rate = values.index_rate
+        self.gui_config.n_cpu = values.n_cpu
+        self.gui_config.use_pv = values.use_pv
+        self.gui_config.f0method = values.f0method
+        return True
+
+    def start_vc(self):
+        torch.cuda.empty_cache()
+        self.flag_vc = True
+        self.rvc = rvc_for_realtime.RVC(
+            self.gui_config.pitch,
+            self.gui_config.pth_path,
+            self.gui_config.index_path,
+            self.gui_config.index_rate,
+            self.gui_config.n_cpu,
+            self.inp_q,
+            self.opt_q,
+            self.config,
+            self.rvc if self.rvc else None,
+        )
+        self.gui_config.samplerate = (
+            self.rvc.tgt_sr
+            if self.gui_config.sr_type == "sr_model"
+            else self.get_device_samplerate()
+        )
+        self.zc = self.gui_config.samplerate // 100
+        self.block_frame = (
+            int(
+                np.round(
+                    self.gui_config.block_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.block_frame_16k = 160 * self.block_frame // self.zc
+        self.crossfade_frame = (
+            int(
+                np.round(
+                    self.gui_config.crossfade_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.sola_buffer_frame = min(self.crossfade_frame, 4 * self.zc)
+        self.sola_search_frame = self.zc
+        self.extra_frame = (
+            int(
+                np.round(
+                    self.gui_config.extra_time
+                    * self.gui_config.samplerate
+                    / self.zc
+                )
+            )
+            * self.zc
+        )
+        self.input_wav = torch.zeros(
+            self.extra_frame
+            + self.crossfade_frame
+            + self.sola_search_frame
+            + self.block_frame,
+            device=self.config.device,
+            dtype=torch.float32,
+        )
+        self.input_wav_denoise = self.input_wav.clone()
+        self.input_wav_res = torch.zeros(
+            160 * self.input_wav.shape[0] // self.zc,
+            device=self.config.device,
+            dtype=torch.float32,
+        )
+        self.rms_buffer = np.zeros(4 * self.zc, dtype="float32")
+        self.sola_buffer = torch.zeros(
+            self.sola_buffer_frame, device=self.config.device, dtype=torch.float32
+        )
+        self.nr_buffer = self.sola_buffer.clone()
+        self.output_buffer = self.input_wav.clone()
+        self.skip_head = self.extra_frame // self.zc
+        self.return_length = (
+            self.block_frame + self.sola_buffer_frame + self.sola_search_frame
+        ) // self.zc
+        self.fade_in_window = (
+            torch.sin(
+                0.5
+                * np.pi
+                * torch.linspace(
+                    0.0,
+                    1.0,
+                    steps=self.sola_buffer_frame,
+                    device=self.config.device,
+                    dtype=torch.float32,
+                )
+            )
+            ** 2
+        )
+        self.fade_out_window = 1 - self.fade_in_window
+        self.resampler = tat.Resample(
+            orig_freq=self.gui_config.samplerate,
+            new_freq=16000,
+            dtype=torch.float32,
+        ).to(self.config.device)
+        if self.rvc.tgt_sr != self.gui_config.samplerate:
+            self.resampler2 = tat.Resample(
+                orig_freq=self.rvc.tgt_sr,
+                new_freq=self.gui_config.samplerate,
+                dtype=torch.float32,
+            ).to(self.config.device)
+        else:
+            self.resampler2 = None
+        self.tg = TorchGate(
+            sr=self.gui_config.samplerate, n_fft=4 * self.zc, prop_decrease=0.9
+        ).to(self.config.device)
+        thread_vc = threading.Thread(target=self.soundinput)
+        thread_vc.start()
+
+    def soundinput(self):
+        channels = 1 if sys.platform == "darwin" else 2
+        with sd.Stream(
+            channels=channels,
+            callback=self.audio_callback,
+            blocksize=self.block_frame,
+            samplerate=self.gui_config.samplerate,
+            dtype="float32",
+        ) as stream:
+            global stream_latency
+            stream_latency = stream.latency[-1]
+            while self.flag_vc:
+                time.sleep(self.gui_config.block_time)
+                logger.info("Audio block passed.")
+        logger.info("Ending VC")
+
+    def audio_callback(self, indata: np.ndarray, outdata: np.ndarray, frames, times, status):
+        start_time = time.perf_counter()
+        indata = librosa.to_mono(indata.T)
+        if self.gui_config.threhold > -60:
+            indata = np.append(self.rms_buffer, indata)
+            rms = librosa.feature.rms(y=indata, frame_length=4 * self.zc, hop_length=self.zc)[:, 2:]
+            self.rms_buffer[:] = indata[-4 * self.zc :]
+            indata = indata[2 * self.zc - self.zc // 2 :]
+            db_threhold = (
+                librosa.amplitude_to_db(rms, ref=1.0)[0] < self.gui_config.threhold
+            )
+            for i in range(db_threhold.shape[0]):
+                if db_threhold[i]:
+                    indata[i * self.zc : (i + 1) * self.zc] = 0
+            indata = indata[self.zc // 2 :]
+        self.input_wav[: -self.block_frame] = self.input_wav[self.block_frame :].clone()
+        self.input_wav[-indata.shape[0] :] = torch.from_numpy(indata).to(self.config.device)
+        self.input_wav_res[: -self.block_frame_16k] = self.input_wav_res[self.block_frame_16k :].clone()
+        # input noise reduction and resampling
+        if self.gui_config.I_noise_reduce:
+            self.input_wav_denoise[: -self.block_frame] = self.input_wav_denoise[self.block_frame :].clone()
+            input_wav = self.input_wav[-self.sola_buffer_frame - self.block_frame :]
+            input_wav = self.tg(input_wav.unsqueeze(0), self.input_wav.unsqueeze(0)).squeeze(0)
+            input_wav[: self.sola_buffer_frame] *= self.fade_in_window
+            input_wav[: self.sola_buffer_frame] += self.nr_buffer * self.fade_out_window
+            self.input_wav_denoise[-self.block_frame :] = input_wav[: self.block_frame]
+            self.nr_buffer[:] = input_wav[self.block_frame :]
+            self.input_wav_res[-self.block_frame_16k - 160 :] = self.resampler(
+                self.input_wav_denoise[-self.block_frame - 2 * self.zc :]
+            )[160:]
+        else:
+            self.input_wav_res[-160 * (indata.shape[0] // self.zc + 1) :] = (
+                self.resampler(self.input_wav[-indata.shape[0] - 2 * self.zc :])[160:]
+            )
+        # infer
+        if self.function == "vc":
+            infer_wav = self.rvc.infer(
+                self.input_wav_res,
+                self.block_frame_16k,
+                self.skip_head,
+                self.return_length,
+                self.gui_config.f0method,
+            )
+            if self.resampler2 is not None:
+                infer_wav = self.resampler2(infer_wav)
+        elif self.gui_config.I_noise_reduce:
+            infer_wav = self.input_wav_denoise[self.extra_frame :].clone()
+        else:
+            infer_wav = self.input_wav[self.extra_frame :].clone()
+        # output noise reduction
+        if self.gui_config.O_noise_reduce and self.function == "vc":
+            self.output_buffer[: -self.block_frame] = self.output_buffer[self.block_frame :].clone()
+            self.output_buffer[-self.block_frame :] = infer_wav[-self.block_frame :]
+            infer_wav = self.tg(infer_wav.unsqueeze(0), self.output_buffer.unsqueeze(0)).squeeze(0)
+        # volume envelop mixing
+        if self.gui_config.rms_mix_rate < 1 and self.function == "vc":
+            if self.gui_config.I_noise_reduce:
+                input_wav = self.input_wav_denoise[self.extra_frame :]
+            else:
+                input_wav = self.input_wav[self.extra_frame :]
+            rms1 = librosa.feature.rms(
+                y=input_wav[: infer_wav.shape[0]].cpu().numpy(),
+                frame_length=4 * self.zc,
+                hop_length=self.zc,
+            )
+            rms1 = torch.from_numpy(rms1).to(self.config.device)
+            rms1 = F.interpolate(
+                rms1.unsqueeze(0),
+                size=infer_wav.shape[0] + 1,
+                mode="linear",
+                align_corners=True,
+            )[0, 0, :-1]
+            rms2 = librosa.feature.rms(
+                y=infer_wav[:].cpu().numpy(),
+                frame_length=4 * self.zc,
+                hop_length=self.zc,
+            )
+            rms2 = torch.from_numpy(rms2).to(self.config.device)
+            rms2 = F.interpolate(
+                rms2.unsqueeze(0),
+                size=infer_wav.shape[0] + 1,
+                mode="linear",
+                align_corners=True,
+            )[0, 0, :-1]
+            rms2 = torch.max(rms2, torch.zeros_like(rms2) + 1e-3)
+            infer_wav *= torch.pow(
+                rms1 / rms2, torch.tensor(1 - self.gui_config.rms_mix_rate)
+            )
+        # SOLA algorithm from https://github.com/yxlllc/DDSP-SVC
+        conv_input = infer_wav[None, None, : self.sola_buffer_frame + self.sola_search_frame]
+        cor_nom = F.conv1d(conv_input, self.sola_buffer[None, None, :])
+        cor_den = torch.sqrt(
+            F.conv1d(
+                conv_input**2,
+                torch.ones(1, 1, self.sola_buffer_frame, device=self.config.device),
+            )
+            + 1e-8
+        )
+        if sys.platform == "darwin":
+            _, sola_offset = torch.max(cor_nom[0, 0] / cor_den[0, 0])
+            sola_offset = sola_offset.item()
+        else:
+            sola_offset = torch.argmax(cor_nom[0, 0] / cor_den[0, 0])
+        logger.info(f"sola_offset = {sola_offset}")
+        infer_wav = infer_wav[sola_offset:]
+        if "privateuseone" in str(self.config.device) or not self.gui_config.use_pv:
+            infer_wav[: self.sola_buffer_frame] *= self.fade_in_window
+            infer_wav[: self.sola_buffer_frame] += self.sola_buffer * self.fade_out_window
+        else:
+            infer_wav[: self.sola_buffer_frame] = phase_vocoder(
+                self.sola_buffer,
+                infer_wav[: self.sola_buffer_frame],
+                self.fade_out_window,
+                self.fade_in_window,
+            )
+        self.sola_buffer[:] = infer_wav[
+            self.block_frame : self.block_frame + self.sola_buffer_frame
+        ]
+        if sys.platform == "darwin":
+            outdata[:] = infer_wav[: self.block_frame].cpu().numpy()[:, np.newaxis]
+        else:
+            outdata[:] = infer_wav[: self.block_frame].repeat(2, 1).t().cpu().numpy()
+        total_time = time.perf_counter() - start_time
+        logger.info(f"Infer time: {total_time:.2f}")
+
+    def get_devices(self, update: bool = True):
+        if update:
+            sd._terminate()
+            sd._initialize()
+        devices = sd.query_devices()
+        hostapis = sd.query_hostapis()
+        for hostapi in hostapis:
+            for device_idx in hostapi["devices"]:
+                devices[device_idx]["hostapi_name"] = hostapi["name"]
+        input_devices = [
+            f"{d['name']} ({d['hostapi_name']})"
+            for d in devices
+            if d["max_input_channels"] > 0
+        ]
+        output_devices = [
+            f"{d['name']} ({d['hostapi_name']})"
+            for d in devices
+            if d["max_output_channels"] > 0
+        ]
+        input_devices_indices = [
+            d["index"] if "index" in d else d["name"]
+            for d in devices
+            if d["max_input_channels"] > 0
+        ]
+        output_devices_indices = [
+            d["index"] if "index" in d else d["name"]
+            for d in devices
+            if d["max_output_channels"] > 0
+        ]
+        return (
+            input_devices,
+            output_devices,
+            input_devices_indices,
+            output_devices_indices,
+        )
+
+    def set_devices(self, input_device, output_device):
+        (
+            input_devices,
+            output_devices,
+            input_device_indices,
+            output_device_indices,
+        ) = self.get_devices()
+        logger.debug(f"Available input devices: {input_devices}")
+        logger.debug(f"Available output devices: {output_devices}")
+        logger.debug(f"Selected input device: {input_device}")
+        logger.debug(f"Selected output device: {output_device}")
+
+        if input_device not in input_devices:
+            logger.error(f"Input device '{input_device}' is not in the list of available devices")
+            raise HTTPException(status_code=400, detail=f"Input device '{input_device}' is not available")
+        
+        if output_device not in output_devices:
+            logger.error(f"Output device '{output_device}' is not in the list of available devices")
+            raise HTTPException(status_code=400, detail=f"Output device '{output_device}' is not available")
+
+        sd.default.device[0] = input_device_indices[input_devices.index(input_device)]
+        sd.default.device[1] = output_device_indices[output_devices.index(output_device)]
+        logger.info(f"Input device set to {sd.default.device[0]}: {input_device}")
+        logger.info(f"Output device set to {sd.default.device[1]}: {output_device}")
+
+audio_api = AudioAPI()
+
+@app.get("/inputDevices", response_model=list)
+def get_input_devices():
+    try:
+        input_devices, _, _, _ = audio_api.get_devices()
+        return input_devices
+    except Exception as e:
+        logger.error(f"Failed to get input devices: {e}")
+        raise HTTPException(status_code=500, detail="Failed to get input devices")
+
+@app.get("/outputDevices", response_model=list)
+def get_output_devices():
+    try:
+        _, output_devices, _, _ = audio_api.get_devices()
+        return output_devices
+    except Exception as e:
+        logger.error(f"Failed to get output devices: {e}")
+        raise HTTPException(status_code=500, detail="Failed to get output devices")
+
+@app.post("/config")
+def configure_audio(config_data: ConfigData):
+    try:
+        logger.info(f"Configuring audio with data: {config_data}")
+        if audio_api.set_values(config_data):
+            settings = config_data.dict()
+            settings["use_jit"] = False
+            with open("configs/config.json", "w", encoding='utf-8') as j:
+                json.dump(settings, j, ensure_ascii=False)
+            logger.info("Configuration set successfully")
+            return {"message": "Configuration set successfully"}
+    except HTTPException as e:
+        logger.error(f"Configuration error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Configuration failed: {e}")
+        raise HTTPException(status_code=400, detail=f"Configuration failed: {e}")
+
+@app.post("/start")
+def start_conversion():
+    try:
+        if not audio_api.flag_vc:
+            audio_api.start_vc()
+            return {"message": "Audio conversion started"}
+        else:
+            logger.warning("Audio conversion already running")
+            raise HTTPException(status_code=400, detail="Audio conversion already running")
+    except HTTPException as e:
+        logger.error(f"Start conversion error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Failed to start conversion: {e}")
+        raise HTTPException(status_code=500, detail="Failed to start conversion: {e}")
+
+@app.post("/stop")
+def stop_conversion():
+    try:
+        if audio_api.flag_vc:
+            audio_api.flag_vc = False
+            global stream_latency
+            stream_latency = -1
+            return {"message": "Audio conversion stopped"}
+        else:
+            logger.warning("Audio conversion not running")
+            raise HTTPException(status_code=400, detail="Audio conversion not running")
+    except HTTPException as e:
+        logger.error(f"Stop conversion error: {e.detail}")
+        raise
+    except Exception as e:
+        logger.error(f"Failed to stop conversion: {e}")
+        raise HTTPException(status_code=500, detail="Failed to stop conversion: {e}")
+
+if __name__ == "__main__":
+    if sys.platform == "win32":
+        freeze_support()
+    load_dotenv()
+    os.environ["OMP_NUM_THREADS"] = "4"
+    if sys.platform == "darwin":
+        os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
+    from tools.torchgate import TorchGate
+    import tools.rvc_for_realtime as rvc_for_realtime
+    from configs.config import Config
+    audio_api.config = Config()
+    audio_api.initialize_queues()
+    uvicorn.run(app, host="0.0.0.0", port=6242)

assets/Synthesizer_inputs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c5ae8cd034b02bbc325939e9b9debbedb43ee9d71a654daaff8804815bd957d
+size 122495

assets/hubert/.gitignore

@@ -0,0 +1,3 @@
+*
+!.gitignore
+!hubert_inputs.pth

assets/hubert/hubert_inputs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbd4741d4be8a71333170c0df5320f605a9d210b96547b391555da078167861f
+size 169434

assets/indices/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

assets/pretrained/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

assets/pretrained_v2/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

assets/pretrained_v2/f0D32k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd7134e7793674c85474d5145d2d982e3c5d8124fc7bb6c20f710ed65808fa8a
+size 142875703

assets/pretrained_v2/f0G32k.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2332611297b8d88c7436de8f17ef5f07a2119353e962cd93cda5806d59a1133d
+size 73950049

assets/pretrained_v2/f0Ov2Super32kD.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2401113af8524bc5c0fe2221a81997b32f85db782f2271bb21d268f2fbf15c56
+size 857123266

assets/pretrained_v2/f0Ov2Super32kG.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4af1279fb8fd15af9eacbb41687fc695e74009e9dd0edc634b6296453324db4
+size 443230526

assets/rmvpe/.gitignore

@@ -0,0 +1,3 @@
+*
+!.gitignore
+!rmvpe_inputs.pth

assets/rmvpe/rmvpe_inputs.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:339fcb7e1476b302e9aecef4a951e918c20852b2e871de5eea13b06e554e0a3a
+size 33527

assets/uvr5_weights/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

configs/config.json

@@ -0,0 +1 @@
+{"pth_path": "assets/weights/kikiV1.pth", "index_path": "logs/kikiV1.index", "sg_hostapi": "MME", "sg_wasapi_exclusive": false, "sg_input_device": "VoiceMeeter Output (VB-Audio Vo", "sg_output_device": "VoiceMeeter Input (VB-Audio Voi", "sr_type": "sr_device", "threhold": -60.0, "pitch": 12.0, "formant": 0.0, "rms_mix_rate": 0.5, "index_rate": 0.0, "block_time": 0.15, "crossfade_length": 0.08, "extra_time": 2.0, "n_cpu": 4.0, "use_jit": false, "use_pv": false, "f0method": "fcpe"}

configs/config.py

@@ -0,0 +1,254 @@
+import argparse
+import os
+import sys
+import json
+import shutil
+from multiprocessing import cpu_count
+
+import torch
+
+try:
+    import intel_extension_for_pytorch as ipex  # pylint: disable=import-error, unused-import
+
+    if torch.xpu.is_available():
+        from infer.modules.ipex import ipex_init
+
+        ipex_init()
+except Exception:  # pylint: disable=broad-exception-caught
+    pass
+import logging
+
+logger = logging.getLogger(__name__)
+
+
+version_config_list = [
+    "v1/32k.json",
+    "v1/40k.json",
+    "v1/48k.json",
+    "v2/48k.json",
+    "v2/32k.json",
+]
+
+
+def singleton_variable(func):
+    def wrapper(*args, **kwargs):
+        if not wrapper.instance:
+            wrapper.instance = func(*args, **kwargs)
+        return wrapper.instance
+
+    wrapper.instance = None
+    return wrapper
+
+
+@singleton_variable
+class Config:
+    def __init__(self):
+        self.device = "cuda:0"
+        self.is_half = True
+        self.use_jit = False
+        self.n_cpu = 0
+        self.gpu_name = None
+        self.json_config = self.load_config_json()
+        self.gpu_mem = None
+        (
+            self.python_cmd,
+            self.listen_port,
+            self.iscolab,
+            self.noparallel,
+            self.noautoopen,
+            self.dml,
+        ) = self.arg_parse()
+        self.instead = ""
+        self.preprocess_per = 3.7
+        self.x_pad, self.x_query, self.x_center, self.x_max = self.device_config()
+
+    @staticmethod
+    def load_config_json() -> dict:
+        d = {}
+        for config_file in version_config_list:
+            p = f"configs/inuse/{config_file}"
+            if not os.path.exists(p):
+                shutil.copy(f"configs/{config_file}", p)
+            with open(f"configs/inuse/{config_file}", "r") as f:
+                d[config_file] = json.load(f)
+        return d
+
+    @staticmethod
+    def arg_parse() -> tuple:
+        exe = sys.executable or "python"
+        parser = argparse.ArgumentParser()
+        parser.add_argument("--port", type=int, default=7865, help="Listen port")
+        parser.add_argument("--pycmd", type=str, default=exe, help="Python command")
+        parser.add_argument("--colab", action="store_true", help="Launch in colab")
+        parser.add_argument(
+            "--noparallel", action="store_true", help="Disable parallel processing"
+        )
+        parser.add_argument(
+            "--noautoopen",
+            action="store_true",
+            help="Do not open in browser automatically",
+        )
+        parser.add_argument(
+            "--dml",
+            action="store_true",
+            help="torch_dml",
+        )
+        cmd_opts = parser.parse_args()
+
+        cmd_opts.port = cmd_opts.port if 0 <= cmd_opts.port <= 65535 else 7865
+
+        return (
+            cmd_opts.pycmd,
+            cmd_opts.port,
+            cmd_opts.colab,
+            cmd_opts.noparallel,
+            cmd_opts.noautoopen,
+            cmd_opts.dml,
+        )
+
+    # has_mps is only available in nightly pytorch (for now) and MasOS 12.3+.
+    # check `getattr` and try it for compatibility
+    @staticmethod
+    def has_mps() -> bool:
+        if not torch.backends.mps.is_available():
+            return False
+        try:
+            torch.zeros(1).to(torch.device("mps"))
+            return True
+        except Exception:
+            return False
+
+    @staticmethod
+    def has_xpu() -> bool:
+        if hasattr(torch, "xpu") and torch.xpu.is_available():
+            return True
+        else:
+            return False
+
+    def use_fp32_config(self):
+        for config_file in version_config_list:
+            self.json_config[config_file]["train"]["fp16_run"] = False
+            with open(f"configs/inuse/{config_file}", "r") as f:
+                strr = f.read().replace("true", "false")
+            with open(f"configs/inuse/{config_file}", "w") as f:
+                f.write(strr)
+            logger.info("overwrite " + config_file)
+        self.preprocess_per = 3.0
+        logger.info("overwrite preprocess_per to %d" % (self.preprocess_per))
+
+    def device_config(self) -> tuple:
+        if torch.cuda.is_available():
+            if self.has_xpu():
+                self.device = self.instead = "xpu:0"
+                self.is_half = True
+            i_device = int(self.device.split(":")[-1])
+            self.gpu_name = torch.cuda.get_device_name(i_device)
+            if (
+                ("16" in self.gpu_name and "V100" not in self.gpu_name.upper())
+                or "P40" in self.gpu_name.upper()
+                or "P10" in self.gpu_name.upper()
+                or "1060" in self.gpu_name
+                or "1070" in self.gpu_name
+                or "1080" in self.gpu_name
+            ):
+                logger.info("Found GPU %s, force to fp32", self.gpu_name)
+                self.is_half = False
+                self.use_fp32_config()
+            else:
+                logger.info("Found GPU %s", self.gpu_name)
+            self.gpu_mem = int(
+                torch.cuda.get_device_properties(i_device).total_memory
+                / 1024
+                / 1024
+                / 1024
+                + 0.4
+            )
+            if self.gpu_mem <= 4:
+                self.preprocess_per = 3.0
+        elif self.has_mps():
+            logger.info("No supported Nvidia GPU found")
+            self.device = self.instead = "mps"
+            self.is_half = False
+            self.use_fp32_config()
+        else:
+            logger.info("No supported Nvidia GPU found")
+            self.device = self.instead = "cpu"
+            self.is_half = False
+            self.use_fp32_config()
+
+        if self.n_cpu == 0:
+            self.n_cpu = cpu_count()
+
+        if self.is_half:
+            # 6G显存配置
+            x_pad = 3
+            x_query = 10
+            x_center = 60
+            x_max = 65
+        else:
+            # 5G显存配置
+            x_pad = 1
+            x_query = 6
+            x_center = 38
+            x_max = 41
+
+        if self.gpu_mem is not None and self.gpu_mem <= 4:
+            x_pad = 1
+            x_query = 5
+            x_center = 30
+            x_max = 32
+        if self.dml:
+            logger.info("Use DirectML instead")
+            if (
+                os.path.exists(
+                    "runtime\Lib\site-packages\onnxruntime\capi\DirectML.dll"
+                )
+                == False
+            ):
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime",
+                        "runtime\Lib\site-packages\onnxruntime-cuda",
+                    )
+                except:
+                    pass
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime-dml",
+                        "runtime\Lib\site-packages\onnxruntime",
+                    )
+                except:
+                    pass
+            # if self.device != "cpu":
+            import torch_directml
+
+            self.device = torch_directml.device(torch_directml.default_device())
+            self.is_half = False
+        else:
+            if self.instead:
+                logger.info(f"Use {self.instead} instead")
+            if (
+                os.path.exists(
+                    "runtime\Lib\site-packages\onnxruntime\capi\onnxruntime_providers_cuda.dll"
+                )
+                == False
+            ):
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime",
+                        "runtime\Lib\site-packages\onnxruntime-dml",
+                    )
+                except:
+                    pass
+                try:
+                    os.rename(
+                        "runtime\Lib\site-packages\onnxruntime-cuda",
+                        "runtime\Lib\site-packages\onnxruntime",
+                    )
+                except:
+                    pass
+        logger.info(
+            "Half-precision floating-point: %s, device: %s"
+            % (self.is_half, self.device)
+        )
+        return x_pad, x_query, x_center, x_max

configs/inuse/.gitignore

@@ -0,0 +1,4 @@
+*
+!.gitignore
+!v1
+!v2

configs/inuse/v1/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

configs/inuse/v2/.gitignore

@@ -0,0 +1,2 @@
+*
+!.gitignore

configs/v1/32k.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 32000,
+    "filter_length": 1024,
+    "hop_length": 320,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,4,2,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

configs/v1/40k.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 40000,
+    "filter_length": 2048,
+    "hop_length": 400,
+    "win_length": 2048,
+    "n_mel_channels": 125,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,10,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

configs/v1/48k.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 11520,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 48000,
+    "filter_length": 2048,
+    "hop_length": 480,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,6,2,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [16,16,4,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

configs/v2/32k.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 12800,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 32000,
+    "filter_length": 1024,
+    "hop_length": 320,
+    "win_length": 1024,
+    "n_mel_channels": 80,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [10,8,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [20,16,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

configs/v2/48k.json

@@ -0,0 +1,46 @@
+{
+  "train": {
+    "log_interval": 200,
+    "seed": 1234,
+    "epochs": 20000,
+    "learning_rate": 1e-4,
+    "betas": [0.8, 0.99],
+    "eps": 1e-9,
+    "batch_size": 4,
+    "fp16_run": true,
+    "lr_decay": 0.999875,
+    "segment_size": 17280,
+    "init_lr_ratio": 1,
+    "warmup_epochs": 0,
+    "c_mel": 45,
+    "c_kl": 1.0
+  },
+  "data": {
+    "max_wav_value": 32768.0,
+    "sampling_rate": 48000,
+    "filter_length": 2048,
+    "hop_length": 480,
+    "win_length": 2048,
+    "n_mel_channels": 128,
+    "mel_fmin": 0.0,
+    "mel_fmax": null
+  },
+  "model": {
+    "inter_channels": 192,
+    "hidden_channels": 192,
+    "filter_channels": 768,
+    "n_heads": 2,
+    "n_layers": 6,
+    "kernel_size": 3,
+    "p_dropout": 0,
+    "resblock": "1",
+    "resblock_kernel_sizes": [3,7,11],
+    "resblock_dilation_sizes": [[1,3,5], [1,3,5], [1,3,5]],
+    "upsample_rates": [12,10,2,2],
+    "upsample_initial_channel": 512,
+    "upsample_kernel_sizes": [24,20,4,4],
+    "use_spectral_norm": false,
+    "gin_channels": 256,
+    "spk_embed_dim": 109
+  }
+}

demo.py

@@ -0,0 +1,1012 @@
+import os
+
+import re
+
+import random
+
+from scipy.io.wavfile import write
+from scipy.io.wavfile import read
+
+import numpy as np
+
+import gradio as gr
+
+import yt_dlp
+
+import subprocess
+
+from original import *
+
+import shutil, glob, subprocess
+
+from easyfuncs import download_from_url, CachedModels, whisperspeak, whisperspeak_on, stereo_process, sr_process
+
+os.makedirs("dataset",exist_ok=True)
+
+os.makedirs("audios",exist_ok=True)
+
+model_library = CachedModels()
+
+
+now_dir = os.getcwd()
+
+
+def download_audio(url):
+    ydl_opts = {
+        'format': 'bestaudio/best',
+        'outtmpl': 'ytdl/%(title)s.%(ext)s',
+        'postprocessors': [{
+            'key': 'FFmpegExtractAudio',
+            'preferredcodec': 'wav',
+            'preferredquality': '192',
+        }],
+    }
+
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        info_dict = ydl.extract_info(url, download=True)
+        file_path = ydl.prepare_filename(info_dict).rsplit('.', 1)[0] + '.wav'
+        sample_rate, audio_data = read(file_path)
+        audio_array = np.asarray(audio_data, dtype=np.int16)
+
+        return sample_rate, audio_array
+
+
+
+def roformer_separator(roformer_audio, roformer_output_format="wav", roformer_overlap="4", roformer_segment_size="256"):
+  files_list = []
+  files_list.clear()
+  directory = f"{now_dir}/audios"
+  random_id = str(random.randint(10000, 99999))
+  pattern = f"{random_id}"
+  output_path = f"{now_dir}/audios"
+  os.makedirs("outputs", exist_ok=True)
+  write(f'{random_id}.wav', roformer_audio[0], roformer_audio[1])
+  full_roformer_model = "model_bs_roformer_ep_317_sdr_12.9755.ckpt"
+  prompt = f"audio-separator {random_id}.wav --model_filename {full_roformer_model} --output_dir={output_path} --output_format={roformer_output_format} --normalization=0.9 --mdxc_overlap={roformer_overlap} --mdxc_segment_size={roformer_segment_size}"
+  os.system(prompt)
+  instrumental_path = f"{output_path}/{random_id}_(Instrumental)_model_bs_roformer_ep_317_sdr_12.wav"
+  os.remove(instrumental_path)
+
+
+  return "audio separating success!"
+
+
+
+
+with gr.Blocks(title="🔊 RYO RVC fork") as app:
+    gr.Markdown("# RYO RVC fork")
+    with gr.Tabs():
+
+        with gr.TabItem("Inference"):
+            voice_model = gr.Dropdown(label="AI Voice", choices=sorted(names), value=lambda:sorted(names)[0] if len(sorted(names)) > 0 else '', interactive=True)
+
+
+            with gr.Row():
+                                  
+              refresh_button = gr.Button("Refresh", variant="primary")
+
+              vc_transform0 = gr.Number(label="Pitch", value=0)
+
+              but0 = gr.Button(value="Convert", variant="primary")
+
+                
+              spk_item = gr.Slider(
+
+                  minimum=0,
+
+                  maximum=2333,
+
+                  step=1,
+
+                  label="Speaker ID",
+
+                  value=0,
+
+                  visible=False,
+
+                  interactive=False,
+
+                )
+
+                
+
+                
+            with gr.Row():
+
+                with gr.Column():
+
+                    with gr.Tabs():
+
+                        with gr.TabItem("Upload"):
+
+                            dropbox = gr.File(label="Drop your audio here & hit the Reload button.")
+
+                        with gr.TabItem("Record"):
+
+                            record_button=gr.Microphone(label="OR Record audio.", type="filepath")
+
+                        with gr.TabItem("UVR"):
+
+                            with gr.Row():
+
+                                roformer_audio = gr.Audio(
+                                    
+                                    label = "Input Audio",
+
+                                    type = "numpy",
+
+                                    interactive = True
+
+                                )
+                            with gr.Accordion("Separation by Link", open=False):                                                       
+                                with gr.Row():
+                                    roformer_link = gr.Textbox(
+                                        label = "Link",
+                                        
+                                        placeholder = "Paste the link here",
+                                    
+                                        interactive = True
+                                    )
+                                with gr.Row():
+                                    gr.Markdown("You can paste the link to the video/audio from many sites, check the complete list [here](https://github.com/yt-dlp/yt-dlp/blob/master/supportedsites.md)")
+                                    
+                                with gr.Row():
+                                    roformer_download_button = gr.Button(
+                                        
+                                        "Download!",
+                                        
+                                        variant = "primary"
+
+                                    )
+
+                            roformer_download_button.click(download_audio, [roformer_link], [roformer_audio])
+
+                            with gr.Row():
+
+                                roformer_button = gr.Button("Separate!", variant = "primary")
+                            with gr.Column():
+                                roformer_stem = gr.Textbox(
+                                    
+                                    interactive = False,
+                                    
+                                    label = "Output",
+                    
+                
+                                )
+                
+                                
+                    with gr.Row():
+
+                        paths_for_files = lambda path:[os.path.abspath(os.path.join(path, f)) for f in os.listdir(path) if os.path.splitext(f)[1].lower() in ('.mp3', '.wav', '.flac', '.ogg')]
+
+                        input_audio0 = gr.Dropdown(
+
+                            label="Input Path",
+
+                            value=paths_for_files('audios')[0] if len(paths_for_files('audios')) > 0 else '',
+
+                            choices=paths_for_files('audios'), # Only show absolute paths for audio files ending in .mp3, .wav, .flac or .ogg
+
+                            allow_custom_value=True
+
+                        )
+
+                    with gr.Row():
+
+                        input_player = gr.Audio(label="Input",type="numpy",interactive=False)
+
+                        input_audio0.change(
+
+                            inputs=[input_audio0],
+
+                            outputs=[input_player],
+
+                            fn=lambda path: {"value":path,"__type__":"update"} if os.path.exists(path) else None
+
+                        )
+
+                        record_button.stop_recording(
+
+                            fn=lambda audio:audio, #TODO save wav lambda
+
+                            inputs=[record_button], 
+
+                            outputs=[input_audio0])
+
+                        dropbox.upload(
+
+                            fn=lambda audio:audio.name,
+
+                            inputs=[dropbox], 
+
+                            outputs=[input_audio0])
+
+                        roformer_button.click(roformer_separator, [roformer_audio], [roformer_stem])
+        
+
+                with gr.Column():
+
+                    with gr.Accordion("Change Index", open=False):
+
+                        file_index2 = gr.Dropdown(
+
+                            label="Change Index",
+
+                            choices=sorted(index_paths),
+
+                            interactive=True,
+
+                            value=sorted(index_paths)[0] if len(sorted(index_paths)) > 0 else ''
+
+                        )
+
+                        index_rate1 = gr.Slider(
+
+                            minimum=0,
+
+                            maximum=1,
+
+                            label="Index Strength",
+
+                            value=0.5,
+
+                            interactive=True,
+
+                        )
+
+                    
+                    with gr.Accordion("General Settings", open=False):
+
+                        f0method0 = gr.Radio(
+
+                            label="Method",
+
+                            choices=["pm", "crepe", "dio", "harvest", "rmvpe"],
+
+                            value="rmvpe",
+
+                            interactive=True,
+
+                            
+
+                        )
+
+                        filter_radius0 = gr.Slider(
+
+                            minimum=0,
+
+                            maximum=7,
+
+                            label="Breathiness Reduction (Harvest only)",
+
+                            value=3,
+
+                            step=1,
+
+                            interactive=True,
+
+                        )
+
+                        resample_sr0 = gr.Slider(
+
+                            minimum=0,
+
+                            maximum=48000,
+
+                            label="Resample",
+
+                            value=0,
+
+                            step=1,
+
+                            interactive=True,
+
+                            visible=False
+
+                        )
+
+                        rms_mix_rate0 = gr.Slider(
+
+                            minimum=0,
+
+                            maximum=1,
+
+                            label="Volume Normalization",
+
+                            value=0,
+
+                            interactive=True,
+
+                        )
+
+                        protect0 = gr.Slider(
+
+                            minimum=0,
+
+                            maximum=0.5,
+
+                            label="Breathiness Protection (0 is enabled, 0.5 is disabled)",
+
+                            value=0.33,
+
+                            step=0.01,
+
+                            interactive=True,
+
+                        )
+
+                        if voice_model != None: 
+
+                            try: vc.get_vc(voice_model.value,protect0,protect0) #load the model immediately for faster inference
+
+                            except: pass
+
+
+
+                    file_index1 = gr.Textbox(
+
+                        label="Index Path",
+
+                        interactive=True,
+
+                        visible=False#Not used here
+
+                    )
+
+                    output_player = gr.Audio(label="Output",interactive=False)
+
+                    refresh_button.click(
+
+                        fn=change_choices,
+
+                        inputs=[],
+
+                        outputs=[voice_model, file_index2],
+
+                        api_name="infer_refresh",
+
+                    )
+
+                    refresh_button.click(
+
+                        fn=lambda:{"choices":paths_for_files('audios'),"__type__":"update"}, #TODO check if properly returns a sorted list of audio files in the 'audios' folder that have the extensions '.wav', '.mp3', '.ogg', or '.flac'
+
+                        inputs=[],
+
+                        outputs = [input_audio0],   
+
+                    )
+
+                    refresh_button.click(
+
+                        fn=lambda:{"value":paths_for_files('audios')[0],"__type__":"update"} if len(paths_for_files('audios')) > 0 else {"value":"","__type__":"update"}, #TODO check if properly returns a sorted list of audio files in the 'audios' folder that have the extensions '.wav', '.mp3', '.ogg', or '.flac'
+
+                        inputs=[],
+
+                        outputs = [input_audio0],   
+
+                    )
+
+            with gr.Row():
+
+                f0_file = gr.File(label="F0 Path", visible=False)
+
+            with gr.Row():
+
+                vc_output1 = gr.Textbox(label="Information", placeholder="Welcome!",visible=False)
+
+                but0.click(
+
+                    vc.vc_single,  
+
+                    [
+
+                        spk_item,
+
+                        input_audio0,
+
+                        vc_transform0,
+
+                        f0_file,
+
+                        f0method0,
+
+                        file_index1,
+
+                        file_index2,
+
+                        index_rate1,
+
+                        filter_radius0,
+
+                        resample_sr0,
+
+                        rms_mix_rate0,
+
+                        protect0,
+
+                    ],
+
+                    [vc_output1, output_player],
+
+                    api_name="infer_convert",
+
+                )  
+
+                voice_model.change(
+
+                    fn=vc.get_vc,
+
+                    inputs=[voice_model, protect0, protect0],
+
+                    outputs=[spk_item, protect0, protect0, file_index2, file_index2],
+
+                    api_name="infer_change_voice",
+
+                )
+
+        with gr.TabItem("Download Models"):
+
+            with gr.Row():
+
+                url_input = gr.Textbox(label="URL to model (i.e. from huggingface)", value="",placeholder="https://...", scale=6)
+
+                name_output = gr.Textbox(label="Save as (if from hf, you may leave it blank)", value="",placeholder="MyModel",scale=2)
+
+                url_download = gr.Button(value="Download Model",scale=2)
+
+                url_download.click(
+
+                    inputs=[url_input,name_output],
+
+                    outputs=[url_input],
+
+                    fn=download_from_url,
+
+                )
+
+            with gr.Row():
+
+                model_browser = gr.Dropdown(choices=list(model_library.models.keys()),label="OR Search Models (Quality UNKNOWN)",scale=5)
+
+                download_from_browser = gr.Button(value="Get",scale=2)
+
+                download_from_browser.click(
+
+                    inputs=[model_browser],
+
+                    outputs=[model_browser],
+
+                    fn=lambda model: download_from_url(model_library.models[model],model),
+
+                )
+
+        with gr.TabItem("Train"):
+
+            with gr.Row():
+
+                with gr.Column():
+
+                    training_name = gr.Textbox(label="Name your model", value="My-Voice",placeholder="My-Voice")
+
+                    np7 = gr.Slider(
+
+                        minimum=0,
+
+                        maximum=config.n_cpu,
+
+                        step=1,
+
+                        label="Number of CPU processes used to extract pitch features",
+
+                        value=1,
+
+                        interactive=False,
+
+                        visible=False
+
+                    )
+
+                    sr2 = gr.Radio(
+
+                        label="Sampling Rate",
+
+                        choices=["40k", "32k"],
+
+                        value="32k",
+
+                        interactive=True,
+
+                        visible=True
+
+                    )
+
+                    if_f0_3 = gr.Radio(
+
+                        label="Will your model be used for singing? If not, you can ignore this.",
+
+                        choices=[True, False],
+
+                        value=True,
+
+                        interactive=True,
+
+                        visible=False
+
+                    )
+
+                    version19 = gr.Radio(
+
+                        label="Version",
+
+                        choices=["v1", "v2"],
+
+                        value="v2",
+
+                        interactive=True,
+
+                        visible=False,
+
+                    )
+
+                    dataset_folder = gr.Textbox(
+
+                        label="dataset folder", value='dataset'
+
+                    )
+
+                    easy_uploader = gr.Files(label="Drop your audio files here",file_types=['audio'])
+
+                    
+
+ 
+
+                    easy_uploader.upload(inputs=[dataset_folder],outputs=[],fn=lambda folder:os.makedirs(folder,exist_ok=True))
+
+                    easy_uploader.upload(
+
+                        fn=lambda files,folder: [shutil.copy2(f.name,os.path.join(folder,os.path.split(f.name)[1])) for f in files] if folder != "" else gr.Warning('Please enter a folder name for your dataset'),
+
+                        inputs=[easy_uploader, dataset_folder], 
+
+                        outputs=[])
+
+                    gpus6 = gr.Textbox(
+
+                        label="Enter the GPU numbers to use separated by -, (e.g. 0-1-2)",
+
+                        value="",
+
+                        interactive=True,
+
+                        visible=False,
+
+                    )
+
+                    gpu_info9 = gr.Textbox(
+
+                        label="GPU Info", value=gpu_info, visible=False
+
+                    )
+
+                    spk_id5 = gr.Slider(
+
+                        minimum=0,
+
+                        maximum=4,
+
+                        step=1,
+
+                        label="Speaker ID",
+
+                        value=0,
+
+                        interactive=True,
+
+                        visible=False
+
+                    )
+
+                    
+
+                with gr.Column():
+
+                    f0method8 = gr.Radio(
+
+                        label="F0 extraction method",
+
+                        choices=["pm", "harvest", "dio", "rmvpe", "rmvpe_gpu"],
+
+                        value="pm",
+
+                        interactive=False,
+
+                        visible=False
+
+                    )
+
+                    gpus_rmvpe = gr.Textbox(
+
+                        label="GPU numbers to use separated by -, (e.g. 0-1-2)",
+
+                        value="",
+
+                        interactive=False,
+
+                        visible=False,
+
+                    )
+
+                    
+
+                    f0method8.change(
+
+                        fn=change_f0_method,
+
+                        inputs=[f0method8],
+
+                        outputs=[gpus_rmvpe],
+
+                    )
+
+                   
+                with gr.Column():
+
+                    total_epoch11 = gr.Slider(
+
+                        minimum=5,
+
+                        maximum=1000,
+
+                        step=5,
+
+                        label="Epochs (more epochs may improve quality but takes longer)",
+
+                        value=100,
+
+                        interactive=True,
+
+                    )
+
+                    
+
+                    with gr.Accordion(label="General Settings", open=False):
+
+                        gpus16 = gr.Textbox(
+
+                            label="GPUs separated by -, (e.g. 0-1-2)",
+
+                            value="0",
+
+                            interactive=True,
+
+                            visible=False,
+
+                        )
+
+                        save_epoch10 = gr.Slider(
+
+                            minimum=1,
+
+                            maximum=50,
+
+                            step=1,
+
+                            label="Weight Saving Frequency",
+
+                            value=25,
+
+                            interactive=True,
+
+                            visible=False
+
+                        )
+
+                        batch_size12 = gr.Slider(
+
+                            minimum=1,
+
+                            maximum=40,
+
+                            step=1,
+
+                            label="Batch Size",
+
+                            value=1,
+
+                            interactive=True,
+
+                            visible=False
+
+                        )
+
+                        if_save_latest13 = gr.Radio(
+
+                            label="Only save the latest model",
+
+                            choices=["yes", "no"],
+
+                            value="yes",
+
+                            interactive=True,
+
+                            visible=False
+
+                        )
+
+                        if_cache_gpu17 = gr.Radio(
+
+                            label="If your dataset is UNDER 10 minutes, cache it to train faster",
+
+                            choices=["yes", "no"],
+
+                            value="no",
+
+                            interactive=True,
+
+                            visible=True
+
+                        )
+
+                        if_save_every_weights18 = gr.Radio(
+
+                            label="Save small model at every save point",
+
+                            choices=["yes", "no"],
+
+                            value="yes",
+
+                            interactive=False,
+
+                            visible=False
+
+                        )
+
+                        with gr.Accordion(label="Change pretrains", open=False):
+
+                            pretrained = lambda sr, letter: [os.path.abspath(os.path.join('assets/pretrained_v2', file)) for file in os.listdir('assets/pretrained_v2') if file.endswith('.pth') and sr in file and letter in file]
+
+                            pretrained_G14 = gr.Dropdown(
+
+                                label="pretrained G",
+
+                                # Get a list of all pretrained G model files in assets/pretrained_v2 that end with .pth
+
+                                choices = pretrained(sr2.value, 'G'),
+
+                                value=pretrained(sr2.value, 'G')[0] if len(pretrained(sr2.value, 'G')) > 0 else '',
+
+                                interactive=True,
+
+                                visible=True
+
+                            )
+
+                            pretrained_D15 = gr.Dropdown(
+
+                                label="pretrained D",
+
+                                choices = pretrained(sr2.value, 'D'),
+
+                                value= pretrained(sr2.value, 'D')[0] if len(pretrained(sr2.value, 'G')) > 0 else '',
+
+                                visible=True,
+
+                                interactive=True
+
+                            )
+
+                        
+                    with gr.Row():
+                        but1 = gr.Button("1. Process", variant="primary")
+
+                        but2 = gr.Button("2. Extract Features", variant="primary")
+
+                        but4 = gr.Button("3. Train Index", variant="primary")
+
+                        but3 = gr.Button("4. Train Model", variant="primary")
+
+                        info3 = gr.Textbox(label="Information", value="", max_lines=10)
+
+
+                        download_model = gr.Button('5.Download Model')
+
+                    with gr.Row():
+
+                        model_files = gr.Files(label='Your Model and Index file can be downloaded here:')
+
+                        download_model.click(
+
+                            fn=lambda name: os.listdir(f'assets/weights/{name}') + glob.glob(f'logs/{name.split(".")[0]}/added_*.index'),
+
+                            inputs=[training_name], 
+
+                            outputs=[model_files, info3])
+
+                    with gr.Row():
+
+                        sr2.change(
+
+                            change_sr2,
+
+                            [sr2, if_f0_3, version19],
+
+                            [pretrained_G14, pretrained_D15],
+
+                        )
+
+                        version19.change(
+
+                            change_version19,
+
+                            [sr2, if_f0_3, version19],
+
+                            [pretrained_G14, pretrained_D15, sr2],
+
+                        )
+
+                        if_f0_3.change(
+
+                            change_f0,
+
+                            [if_f0_3, sr2, version19],
+
+                            [f0method8, pretrained_G14, pretrained_D15],
+
+                        )
+
+                    with gr.Row():
+
+                        but5 = gr.Button("1 Click Training", variant="primary", visible=False)
+
+                        but1.click(
+                            
+                            preprocess_dataset,
+                            
+                            [dataset_folder, training_name, sr2, np7],
+                            
+                            [info3],
+                            
+                            api_name="train_preprocess",
+                        
+                        ) 
+
+                        but2.click(
+                            extract_f0_feature,
+                            [
+                                gpus6,
+                                
+                                np7,
+                                
+                                f0method8,
+                                
+                                if_f0_3,
+                                
+                                training_name,
+                                
+                                version19,
+
+                                gpus_rmvpe,
+                            
+                            ],
+                            
+                            [info3],
+                            
+                            api_name="train_extract_f0_feature",
+                        
+                        )
+
+
+                        but3.click(
+
+                            click_train,
+
+                            [
+
+                                training_name,
+
+                                sr2,
+
+                                if_f0_3,
+
+                                spk_id5,
+
+                                save_epoch10,
+
+                                total_epoch11,
+
+                                batch_size12,
+
+                                if_save_latest13,
+
+                                pretrained_G14,
+
+                                pretrained_D15,
+
+                                gpus16,
+
+                                if_cache_gpu17,
+
+                                if_save_every_weights18,
+
+                                version19,
+
+                            ],
+
+                            info3,
+
+                            api_name="train_start",
+
+                        )
+
+                        but4.click(train_index, [training_name, version19], info3)
+
+                        but5.click(
+
+                            train1key,
+
+                            [
+
+                                training_name,
+
+                                sr2,
+
+                                if_f0_3,
+
+                                dataset_folder,
+
+                                spk_id5,
+
+                                np7,
+
+                                f0method8,
+
+                                save_epoch10,
+
+                                total_epoch11,
+
+                                batch_size12,
+
+                                if_save_latest13,
+
+                                pretrained_G14,
+
+                                pretrained_D15,
+
+                                gpus16,
+
+                                if_cache_gpu17,
+
+                                if_save_every_weights18,
+
+                                version19,
+
+                                gpus_rmvpe,
+
+                            ],
+
+                            info3,
+
+                            api_name="train_start_all",
+
+                        )
+
+
+
+    if config.iscolab:
+
+        app.queue(max_size=20).launch(share=True,allowed_paths=["a.png"],show_error=True)
+
+    else:
+
+        app.queue(max_size=1022).launch(
+
+            server_name="0.0.0.0",
+
+            inbrowser=not config.noautoopen,
+
+            server_port=config.listen_port,
+
+            quiet=True,
+
+        )

docker-compose.yml

@@ -0,0 +1,20 @@
+version: "3.8"
+services:
+  rvc:
+    build:
+      context: .
+      dockerfile: Dockerfile
+    container_name: rvc
+    volumes:
+      - ./weights:/app/assets/weights
+      - ./opt:/app/opt
+      # - ./dataset:/app/dataset # you can use this folder in order to provide your dataset for model training
+    ports:
+      - 7865:7865
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]

docs/cn/Changelog_CN.md

@@ -0,0 +1,109 @@
+### 20231006更新
+
+我们制作了一个用于实时变声的界面go-realtime-gui.bat/gui_v1.py（事实上早就存在了），本次更新重点也优化了实时变声的性能。对比0813版：
+ - 1、优优化界面操作：参数热更新（调整参数不需要中止再启动），懒加载模型（已加载过的模型不需要重新加载），增加响度因子参数（响度向输入音频靠近）
+ - 2、优化自带降噪效果与速度
+ - 3、大幅优化推理速度
+
+注意输入输出设备应该选择同种类型，例如都选MME类型。
+
+1006版本整体的更新为：
+ - 1、继续提升rmvpe音高提取算法效果，对于男低音有更大的提升
+ - 2、优化推理界面布局
+
+### 20230813更新
+1-常规bug修复
+ - 保存频率总轮数最低改为1 总轮数最低改为2
+ - 修复无pretrain模型训练报错
+ - 增加伴奏人声分离完毕清理显存
+ - faiss保存路径绝对路径改为相对路径
+ - 支持路径包含空格（训练集路径+实验名称均支持，不再会报错）
+ - filelist取消强制utf8编码
+ - 解决实时变声中开启索引导致的CPU极大占用问题
+
+2-重点更新
+ - 训练出当前最强开源人声音高提取模型RMVPE，并用于RVC的训练、离线/实时推理，支持pytorch/onnx/DirectML
+ - 通过pytorch-dml支持A卡和I卡的
+（1）实时变声（2）推理（3）人声伴奏分离（4）训练暂未支持，会切换至CPU训练；通过onnx_dml支持rmvpe_gpu的推理
+
+### 20230618更新
+- v2增加32k和48k两个新预训练模型
+- 修复非f0模型推理报错
+- 对于超过一小时的训练集的索引建立环节，自动kmeans缩小特征处理以加速索引训练、加入和查询
+- 附送一个人声转吉他玩具仓库
+- 数据处理剔除异常值切片
+- onnx导出选项卡
+
+失败的实验：
+- ~~特征检索增加时序维度：寄，没啥效果~~
+- ~~特征检索增加PCAR降维可选项：寄，数据大用kmeans缩小数据量，数据小降维操作耗时比省下的匹配耗时还多~~
+- ~~支持onnx推理（附带仅推理的小压缩包）：寄，生成nsf还是需要pytorch~~
+- ~~训练时在音高、gender、eq、噪声等方面对输入进行随机增强：寄，没啥效果~~
+- ~~接入小型声码器调研:寄，效果变差~~
+
+todolist：
+- ~~训练集音高识别支持crepe：已经被RMVPE取代，不需要~~
+- ~~多进程harvest推理：已经被RMVPE取代，不需要~~
+- ~~crepe的精度支持和RVC-config同步：已经被RMVPE取代，不需要。支持这个还要同步torchcrepe的库，麻烦~~
+- 对接F0编辑器
+  
+  
+### 20230528更新
+- 增加v2的jupyter notebook，韩文changelog，增加一些环境依赖
+- 增加呼吸、清辅音、齿音保护模式
+- 支持crepe-full推理
+- UVR5人声伴奏分离加上3个去延迟模型和MDX-Net去混响模型，增加HP3人声提取模型
+- 索引名称增加版本和实验名称
+- 人声伴奏分离、推理批量导出增加音频导出格式选项
+- 废弃32k模型的训练
+
+### 20230513更新
+- 清除一键包内部老版本runtime内残留的lib.infer_pack和uvr5_pack
+- 修复训练集预处理伪多进程的bug
+- 增加harvest识别音高可选通过中值滤波削弱哑音现象，可调整中值滤波半径
+- 导出音频增加后处理重采样
+- 训练n_cpu进程数从"仅调整f0提取"改为"调整数据预处理和f0提取"
+- 自动检测logs文件夹下的index路径，提供下拉列表功能
+- tab页增加"常见问题解答"（也可参考github-rvc-wiki）
+- 相同路径的输入音频推理增加了音高缓存（用途：使用harvest音高提取，整个pipeline会经历漫长且重复的音高提取过程，如果不使用缓存，实验不同音色、索引、音高中值滤波半径参数的用户在第一次测试后的等待结果会非常痛苦）
+
+### 20230514更新
+- 音量包络对齐输入混合（可以缓解“输入静音输出小幅度噪声”的问题。如果输入音频背景底噪大则不建议开启，默认不开启（值为1可视为不开启））
+- 支持按照指定频率保存提取的小模型（假如你想尝试不同epoch下的推理效果，但是不想保存所有大checkpoint并且每次都要ckpt手工处理提取小模型，这项功能会非常实用）
+- 通过设置环境变量解决服务端开了系统全局代理导致浏览器连接错误的问题
+- 支持v2预训练模型（目前只公开了40k版本进行测试，另外2个采样率还没有训练完全）
+- 推理前限制超过1的过大音量
+- 微调数据预处理参数
+
+
+### 20230409更新
+- 修正训练参数，提升显卡平均利用率，A100最高从25%提升至90%左右，V100:50%->90%左右，2060S:60%->85%左右，P40:25%->95%左右，训练速度显著提升
+- 修正参数：总batch_size改为每张卡的batch_size
+- 修正total_epoch：最大限制100解锁至1000；默认10提升至默认20
+- 修复ckpt提取识别是否带音高错误导致推理异常的问题
+- 修复分布式训练每个rank都保存一次ckpt���问题
+- 特征提取进行nan特征过滤
+- 修复静音输入输出随机辅音or噪声的问题（老版模型需要重做训练集重训）
+
+### 20230416更新
+- 新增本地实时变声迷你GUI，双击go-realtime-gui.bat启动
+- 训练推理均对<50Hz的频段进行滤波过滤
+- 训练推理音高提取pyworld最低音高从默认80下降至50,50-80hz间的男声低音不会哑
+- WebUI支持根据系统区域变更语言（现支持en_US，ja_JP，zh_CN，zh_HK，zh_SG，zh_TW，不支持的默认en_US）
+- 修正部分显卡识别（例如V100-16G识别失败，P4识别失败）
+
+### 20230428更新
+- 升级faiss索引设置，速度更快，质量更高
+- 取消total_npy依赖，后续分享模型不再需要填写total_npy
+- 解锁16系限制。4G显存GPU给到4G的推理设置。
+- 修复部分音频格式下UVR5人声伴奏分离的bug
+- 实时变声迷你gui增加对非40k与不懈怠音高模型的支持
+
+### 后续计划：
+功能：
+- 支持多人训练选项卡（至多4人）
+
+底模：
+- 收集呼吸wav加入训练集修正呼吸变声电音的问题
+- 我们正在训练增加了歌声训练集的底模，未来会公开
+

docs/cn/faq.md

@@ -0,0 +1,108 @@
+## Q1:ffmpeg error/utf8 error.
+
+大概率不是ffmpeg问题，而是音频路径问题；<br>
+ffmpeg读取路径带空格、()等特殊符号，可能出现ffmpeg error；训练集音频带中文路径，在写入filelist.txt的时候可能出现utf8 error；<br>
+
+## Q2:一键训练结束没有索引
+
+显示"Training is done. The program is closed."则模型训练成功，后续紧邻的报错是假的；<br>
+
+一键训练结束完成没有added开头的索引文件，可能是因为训练集太大卡住了添加索引的步骤；已通过批处理add索引解决内存add索引对内存需求过大的问题。临时可尝试再次点击"训练索引"按钮。<br>
+
+## Q3:训练结束推理没看到训练集的音色
+点刷新音色再看看，如果还没有看看训练有没有报错，控制台和webui的截图，logs/实验名下的log，都可以发给开发者看看。<br>
+
+## Q4:如何分享模型
+  rvc_root/logs/实验名 下面存储的pth不是用来分享模型用来推理的，而是为了存储实验状态供复现，以及继续训练用的。用来分享的模型应该是weights文件夹下大小为60+MB的pth文件；<br>
+  后续将把weights/exp_name.pth和logs/exp_name/added_xxx.index合并打包成weights/exp_name.zip省去填写index的步骤，那么zip文件用来分享，不要分享pth文件，除非是想换机器继续训练；<br>
+  如果你把logs文件夹下的几百MB的pth文件复制/分享到weights文件夹下强行用于推理，可能会出现f0，tgt_sr等各种key不存在的报错。你需要用ckpt选项卡最下面，手工或自动（本地logs下如果能找到相关信息则会自动）选择是否携带音高、目标音频采样率的选项后进行ckpt小模型提取（输入路径填G开头的那个），提取完在weights文件夹下会出现60+MB的pth文件，刷新音色后可以选择使用。<br>
+
+## Q5:Connection Error.
+也许你关闭了控制台（黑色窗口）。<br>
+
+## Q6:WebUI弹出Expecting value: line 1 column 1 (char 0).
+请关闭系统局域网代理/全局代理。<br>
+
+这个不仅是客户端的代理，也包括服务端的代理（例如你使用autodl设置了http_proxy和https_proxy学术加速，使用时也需要unset关掉）<br>
+
+## Q7:不用WebUI如何通过命令训练推理
+训练脚本：<br>
+可先跑通WebUI，消息窗内会显示数据集处理和训练用命令行；<br>
+
+推理脚本：<br>
+https://huggingface.co/lj1995/VoiceConversionWebUI/blob/main/myinfer.py<br>
+
+例子：<br>
+
+runtime\python.exe myinfer.py 0 "E:\codes\py39\RVC-beta\todo-songs\1111.wav" "E:\codes\py39\logs\mi-test\added_IVF677_Flat_nprobe_7.index" harvest "test.wav" "weights/mi-test.pth" 0.6 cuda:0 True<br>
+
+f0up_key=sys.argv[1]<br>
+input_path=sys.argv[2]<br>
+index_path=sys.argv[3]<br>
+f0method=sys.argv[4]#harvest or pm<br>
+opt_path=sys.argv[5]<br>
+model_path=sys.argv[6]<br>
+index_rate=float(sys.argv[7])<br>
+device=sys.argv[8]<br>
+is_half=bool(sys.argv[9])<br>
+
+## Q8:Cuda error/Cuda out of memory.
+小概率是cuda配置问题、设备不支持；大概率是显存不够（out of memory）；<br>
+
+训练的话缩小batch size（如果缩小到1还不够只能更换显卡训练），推理的话酌情缩小config.py结尾的x_pad，x_query，x_center，x_max。4G以下显存（例如1060（3G）和各种2G显卡）可以直接放弃，4G显存显卡还有救。<br>
+
+## Q9:total_epoch调多少比较好
+
+如果训练集音质差底噪大，20~30足够了，调太高，底模音质无法带高你的低音质训练集<br>
+如果训练集音质高底噪低时长多，可以调高，200是ok的（训练速度很快，既然你有条件准备高音质训练集，显卡想必条件也不错，肯定不在乎多一些训练时间）<br>
+
+## Q10:需要多少训练集时长
+  推荐10min至50min<br>
+  保证音质高底噪低的情况下，如果有个人特色的音色统一，则多多益善<br>
+  高水平的训练集（精简+音色有特色），5min至10min也是ok的，仓库作者本人就经常这么玩<br>
+  也有人拿1min至2min的数据来训练并且训练成功的，但是成功经验是其他人不可复现的，不太具备参考价值。这要求训练集音色特色非常明显（比如说高频气声较明显的萝莉少女音），且音质高；<br>
+  1min以下时长数据目前没见有人尝试（成功）过。不建议进行这种鬼畜行为。<br>
+
+## Q11:index rate干嘛用的，怎么调（科普）
+  如果底模和推理源的音质高于训练集的音质，他们可以带高推理结果的音质，但代价可能是音色往底模/推理源的音色靠，这种现象叫做"音色泄露"；<br>
+  index rate用来削减/解决音色泄露问题。调到1，则理论上不存在推理源的音色泄露问题，但音质更倾向于训练集。如果训练集音质比推理源低，则index rate调高可能降低音质。调到0，则不具备利用检索混合来保护训练集音色的效果；<br>
+  如果训练集优质时长多，可调高total_epoch，此时模型本身不太会引用推理源和底模的音色，很少存在"音色泄露"问题，此时index_rate不重要，你甚至可以不建立/分享index索引文件。<br>
+
+## Q11:推理怎么选gpu
+config.py文件里device cuda:后面选择卡号；<br>
+卡号和显卡的映射关系，在训练选项卡的显卡信息栏里能看到。<br>
+
+## Q12:如何推理训练中间保存的pth
+通过ckpt选项卡最下面提取小模型。<br>
+
+
+## Q13:如何中断和继续训练
+现阶段只能关闭WebUI控制台双击go-web.bat重启程序。网页参数也要刷新重新填写；<br>
+继续训练：相同网页参数点训练模型，就会接着上次的checkpoint继续训练。<br>
+
+## Q14:训练时出现文件页面/内存error
+进程开太多了，内存炸了。你可能可以通过如下方式解决<br>
+1、"提取音高和处理数据使用的CPU进程数"  酌情拉低；<br>
+2、训练集音频手工切一下，不要太长。<br>
+
+
+## Q15:如何中途加数据训练
+1、所有数据新建一个实验名；<br>
+2、拷贝上一次的最新的那个G和D文件（或者你想基于哪个中间ckpt训练，也可以拷贝中间的）到新实验名；下<br>
+3、一键训练新实验名，他会继续上一次的最新进度训练。<br>
+
+## Q16: error about llvmlite.dll
+
+OSError: Could not load shared object file: llvmlite.dll
+
+FileNotFoundError: Could not find module lib\site-packages\llvmlite\binding\llvmlite.dll (or one of its dependencies). Try using the full path with constructor syntax.
+
+win平台会报这个错，装上https://aka.ms/vs/17/release/vc_redist.x64.exe这个再重启WebUI就好了。
+
+## Q17: RuntimeError: The expanded size of the tensor (17280) must match the existing size (0) at non-singleton dimension 1.  Target sizes: [1, 17280].  Tensor sizes: [0]
+
+wavs16k文件夹下，找到文件大小显著比其他都小的一些音频文件，删掉，点击训练模型，就不会报错了，不过由于一键流程中断了你训练完模型还要点训练索引。
+
+## Q18: RuntimeError: The size of tensor a (24) must match the size of tensor b (16) at non-singleton dimension 2
+
+不要中途变更采样率继续训练。如果一定要变更，应更换实验名从头训练。当然你也可以把上次提取的音高和特征（0/1/2/2b folders）拷贝过去加速训练流程。