Duplicate from mdnestor/tortoise

Co-authored-by: Michael Nestor <mdnestor@users.noreply.huggingface.co>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,14 @@
+---
+title: Tortoise
+emoji: 🎧
+colorFrom: blue
+colorTo: pink
+sdk: gradio
+sdk_version: 3.12.0
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: mdnestor/tortoise
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+import os
+import sys
+
+os.system("git clone https://github.com/neonbjb/tortoise-tts.git")
+sys.path.append("./tortoise-tts/")
+os.system("pip install -r ./tortoise-tts/requirements.txt")
+os.system("python ./tortoise-tts/setup.py install")
+
+import torch
+import torchaudio
+import torch.nn as nn
+import torch.nn.functional as F
+
+from tortoise.api import TextToSpeech
+from tortoise.utils.audio import load_audio, load_voice, load_voices
+
+tts = TextToSpeech()
+
+def main(text, voice, preset):
+  voice_samples, conditioning_latents = load_voice(voice)
+  gen = tts.tts_with_preset(text, voice_samples=voice_samples, conditioning_latents=conditioning_latents, preset=preset)
+  torchaudio.save("generated.wav", gen.squeeze(0).cpu(), 24000)
+  return "generated.wav"
+
+voices = ["mol", "tom", "applejack", "daniel", "myself", "weaver", "train_empire", "train_dotrice", "rainbow", "pat", "geralt", "halle", "train_kennard", "jlaw", "train_grace", "angie", "william", "tim_reynolds", "train_atkins", "train_dreams", "train_mouse", "freeman", "deniro", "lj", "train_lescault", "emma", "pat2", "snakes", "train_daws"]
+presets = ["ultra_fast", "fast", "standard", "high_quality"]
+
+gr.Interface(
+  main, 
+  [
+    gr.Textbox(label="Text", placeholder="Text-to-speak goes here..."),
+    gr.Dropdown(voices, value="deniro", label="Voice"),
+    gr.Dropdown(presets, value="ultra_fast", label="Preset"),
+  ],
+  gr.Audio(),
+  description="TorToiSe - a multi-voice TTS system by <a href=\"https://huggingface.co/jbetker\">jbetker</a> | <a href=\"https://github.com/neonbjb/tortoise-tts\">src</a>\nNote: inference is very slow on CPU; for quicker inference times use the <a href=\"https://github.com/neonbjb/tortoise-tts#usage-guide\">Colab notebook</a> linked in the source repository.",
+  enable_queue=True
+).launch()

requirements.txt

@@ -0,0 +1,2 @@
+torch
+torchaudio