deepgeek/CosyVoice
2
0
Fork 0
mirror of https://github.com/FunAudioLLM/CosyVoice.git synced 2026-02-04 17:39:25 +08:00
Code Issues Packages Projects Releases Wiki Activity

update readme

Browse Source
This commit is contained in:
lyuxiang.lx
2025-12-31 11:28:47 +08:00
parent 881177287c
commit 46788c7379
1 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

12
README.md
View File

@@ -61,7 +61,7 @@
## Evaluation ## Evaluation
| Model | Open-Source | Model Size | test-zh<br>CER (%) ↓ | test-zh<br>Speaker Similarity (%) ↑ | test-en<br>WER (%) ↓ | test-en<br>Speaker Similarity (%) ↑ | test-hard<br>CER (%) ↓ | test-hard<br>Speaker Similarity (%) ↑ | | Model | Open-Source | Model Size | test-zh<br>CER (%) ↓ | test-zh<br>SS (%) ↑ | test-en<br>WER (%) ↓ | test-en<br>SS (%) ↑ | test-hard<br>CER (%) ↓ | test-hard<br>SS (%) ↑ |
| :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: | | :--- | :---: | :---: | :---: | :---: | :---: | :---: | :---: | :---: |
| Human | - | - | 1.26 | 75.5 | 2.14 | 73.4 | - | - | | Human | - | - | 1.26 | 75.5 | 2.14 | 73.4 | - | - |
| Seed-TTS | ❌ | - | 1.12 | 79.6 | 2.25 | 76.2 | 7.59 | 77.6 | | Seed-TTS | ❌ | - | 1.12 | 79.6 | 2.25 | 76.2 | 7.59 | 77.6 |
@@ -151,11 +151,11 @@ Follow the code in `example.py` for detailed usage of each model.
python example.py python example.py
``` ```
#### CosyVoice2 vllm Usage #### vLLM Usage
CosyVoice2 now supports **vLLM 0.11.x+ (V1 engine)** and **vLLM 0.9.0 (legacy)**. CosyVoice2/3 now supports **vLLM 0.11.x+ (V1 engine)** and **vLLM 0.9.0 (legacy)**.
Older vllm version(<0.9.0) do not support CosyVoice2 inference, and versions in between (e.g., 0.10.x) are not tested. Older vllm version(<0.9.0) do not support CosyVoice inference, and versions in between (e.g., 0.10.x) are not tested.
Notice that `vllm==v0.9.0` has a lot of specific requirements, for example `torch==2.7.0`. You can create a new env to in case your hardward do not support vllm and old env is corrupted. Notice that `vllm` has a lot of specific requirements. You can create a new env to in case your hardward do not support vllm and old env is corrupted.
``` sh ``` sh
conda create -n cosyvoice_vllm --clone cosyvoice conda create -n cosyvoice_vllm --clone cosyvoice
@@ -180,7 +180,7 @@ python3 webui.py --port 50000 --model_dir pretrained_models/CosyVoice-300M
#### Advanced Usage #### Advanced Usage
For advanced users, we have provided training and inference scripts in `examples/libritts/cosyvoice/run.sh`. For advanced users, we have provided training and inference scripts in `examples/libritts`.
#### Build for deployment #### Build for deployment