deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-05 18:09:24 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'main' into dev/lyuxiang.lx

Browse Source
This commit is contained in:
Xiang Lyu
2025-05-30 17:16:22 +08:00
committed by GitHub
parent 7d9d84d32d b6c5f9dfd2
commit 79b2ea818b
2 changed files with 29 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files

14
README.md
View File

@@ -53,7 +53,7 @@
## Install ## Install
**Clone and install** ### Clone and install
- Clone the repo - Clone the repo
``` sh ``` sh
@@ -80,7 +80,7 @@ sudo apt-get install sox libsox-dev
sudo yum install sox sox-devel sudo yum install sox sox-devel
``` ```
**Model download** ### Model download
We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource. We strongly recommend that you download our pretrained `CosyVoice2-0.5B` `CosyVoice-300M` `CosyVoice-300M-SFT` `CosyVoice-300M-Instruct` model and `CosyVoice-ttsfrd` resource.
@@ -115,7 +115,7 @@ pip install ttsfrd_dependency-0.1-py3-none-any.whl
pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl pip install ttsfrd-0.4.2-cp310-cp310-linux_x86_64.whl
``` ```
**Basic Usage** ### Basic Usage
We strongly recommend using `CosyVoice2-0.5B` for better performance. We strongly recommend using `CosyVoice2-0.5B` for better performance.
Follow code below for detailed usage of each model. Follow code below for detailed usage of each model.
@@ -128,7 +128,7 @@ from cosyvoice.utils.file_utils import load_wav
import torchaudio import torchaudio
``` ```
**CosyVoice2 Usage** #### CosyVoice2 Usage
```python ```python
cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, load_vllm=False, fp16=False) cosyvoice = CosyVoice2('pretrained_models/CosyVoice2-0.5B', load_jit=False, load_trt=False, load_vllm=False, fp16=False)
@@ -214,7 +214,7 @@ for i, j in enumerate(cosyvoice.inference_instruct('在面对挑战时，他展
torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate) torchaudio.save('instruct_{}.wav'.format(i), j['tts_speech'], cosyvoice.sample_rate)
``` ```
**Start web demo** #### Start web demo
You can use our web demo page to get familiar with CosyVoice quickly. You can use our web demo page to get familiar with CosyVoice quickly.
@@ -225,11 +225,11 @@ Please see the demo website for details.
python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M
``` ```
**Advanced Usage** #### Advanced Usage
For advanced user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`. For advanced user, we have provided train and inference scripts in `examples/libritts/cosyvoice/run.sh`.
**Build for deployment** #### Build for deployment
Optionally, if you want service deployment, Optionally, if you want service deployment,
you can run following steps. you can run following steps.

6
requirements.txt
View File

@@ -3,6 +3,8 @@
conformer==0.3.2 conformer==0.3.2
deepspeed==0.15.1; sys_platform == 'linux' deepspeed==0.15.1; sys_platform == 'linux'
diffusers==0.29.0 diffusers==0.29.0
fastapi==0.115.6
fastapi-cli==0.0.4
gdown==5.1.0 gdown==5.1.0
gradio==5.4.0 gradio==5.4.0
grpcio==1.57.0 grpcio==1.57.0
@@ -34,7 +36,5 @@ torch==2.3.1
torchaudio==2.3.1 torchaudio==2.3.1
transformers==4.40.1 transformers==4.40.1
uvicorn==0.30.0 uvicorn==0.30.0
wget==3.2
fastapi==0.115.6
fastapi-cli==0.0.4
WeTextProcessing==1.0.3 WeTextProcessing==1.0.3
wget==3.2