verachen/VoxCPM
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Update Model Weights, use VoxCPM1.5 and model parameters, Supports streaming

Browse Source
This commit is contained in:
vera
2026-01-21 17:52:57 +08:00
parent 721c53fe87
commit 2b0c569b7a
4 changed files with 225 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files

33
README_BW.md
View File

@ -6,10 +6,17 @@ https://github.com/BoardWare-Genius/VoxCPM
| Version | Date | Summary |
|---------|------------|---------------------------------|
| 0.0.2 | 2026-01-21 | Supports streaming |
| 0.0.1 | 2026-01-20 | Initial version |
### 🔄 Version Details
#### 🆕 0.0.2 – *2026-01-21*
- ✅ **Core Features**
- Update Model Weights, use VoxCPM1.5 and model parameters
- Supports streaming
#### 🆕 0.0.1 – *2026-01-20*
- ✅ **Core Features**
@ -20,12 +27,14 @@ https://github.com/BoardWare-Genius/VoxCPM
# Start
```bash
docker pull harbor.bwgdi.com/library/voxcpmtts:0.0.1
docker pull harbor.bwgdi.com/library/voxcpmtts:0.0.2
docker run -d --restart always -p 5001:5000 --gpus all --mount type=bind,source=/Workspace/NAS11/model,target=/models harbor.bwgdi.com/library/voxcpmtts:0.0.1
docker run -d --restart always -p 5001:5000 --gpus all --mount type=bind,source=/Workspace/NAS11/model/Voice/VoxCPM,target=/models harbor.bwgdi.com/library/voxcpmtts:0.0.2
```
# Usage
## Non-streaming
```bash
curl --location 'http://localhost:5001/generate_tts' \
--form 'text="你好，这是一段测试文本"' \
@ -34,5 +43,23 @@ curl --location 'http://localhost:5001/generate_tts' \
--form 'inference_timesteps="10"' \
--form 'do_normalize="true"' \
--form 'denoise="true"' \
--form 'prompt_wav=@"/assets/2play16k_2.wav"'
--form 'retry_badcase="true"' \
--form 'retry_badcase_max_times="3"' \
--form 'retry_badcase_ratio_threshold="6.0"' \
--form 'prompt_wav=@"/assets/2food16k_2.wav"'
```
## Streaming
```bash
curl --location 'http://localhost:5001/generate_tts_streaming' \
--form 'text="你好，这是一段测试文本"' \
--form 'prompt_text="这是提示文本"' \
--form 'cfg_value="2.0"' \
--form 'inference_timesteps="10"' \
--form 'do_normalize="true"' \
--form 'denoise="true"' \
--form 'retry_badcase="true"' \
--form 'retry_badcase_max_times="3"' \
--form 'retry_badcase_ratio_threshold="6.0"' \
--form 'prompt_wav=@"/Workspace/NAS11/model/Voice/assets/2food16k_2.wav"'
```