README.md

---
license: mit
language:
- en
---

# Pretrained Model of Amphion Vall-E

We provide the pre-trained checkpoint of [Vall-E](https://github.com/open-mmlab/Amphion/tree/main/egs/tts/VALLE) trained on [LibriTTS](https://github.com/open-mmlab/Amphion/tree/main/egs/datasets#libritts), which is is a multi-speaker English corpus of approximately 585 hours of read English speech at 24kHz.



## Quick Start

To utilize the pretrained models, just run the following commands:

### Step1: Download the checkpoint
```bash
git lfs install
git clone https://huggingface.co/amphion/valle_libritts
```

### Step2: Clone the Amphion's Source Code of GitHub
```bash
git clone https://github.com/open-mmlab/Amphion.git
```

### Step3: Specify the checkpoint's path
Use the soft link to specify the downloaded checkpoint in the first step:

```bash
cd Amphion
mkdir -p ckpts/tts
ln -s  ../../../valle_libritts  ckpts/tts/
```

### Step4: Inference

You can follow the inference part of [this recipe](https://github.com/open-mmlab/Amphion/tree/main/egs/tts/VALLE#4-inference) to generate speech from text. For example, if you want to synthesize a clip of speech with the text of "This is a clip of generated speech with the given text from Amphion Vall-E model.", just, run:

```bash
sh egs/tts/VALLE/run.sh --stage 3 --gpu "0" \
    --config "ckpts/tts/valle_libritts/args.json" \
    --infer_expt_dir Amphion/ckpts/tts/valle_libritts \
    --infer_output_dir Amphion/ckpts/tts/valle_libritts/result \
    --infer_mode "single" \
    --infer_text "This is a clip of generated speech with the given text from Amphion Vall-E model." \
    --infer_text_prompt "But even the unsuccessful dramatist has his moments." \
    --infer_audio_prompt egs/tts/VALLE/prompt_examples/7176_92135_000004_000000.wav
```