Paraformer-zh模型不加载VAD模型无法识别标点 - Githubissues

modelscope / FunASR

A Fundamental End-to-End Speech Recognition Toolkit and Open Source SOTA Pretrained Models, Supporting Speech Recognition, Voice Activity Detection, Text Post-processing etc.

https://www.funasr.com

Other

6.15k stars 657 forks source link

Paraformer-zh模型不加载VAD模型无法识别标点 #2064

Closed SinlinLi closed 2 weeks ago

SinlinLi commented 3 weeks ago

Notice: In order to resolve issues more efficiently, please raise issue following the template. （注意：为了更加高效率解决您遇到的问题，请按照模板提问，补充细节）

🐛 Bug

Paraformer-zh模型不加载VAD模型无法识别标点

To Reproduce

因为我这边的业务已经先过一遍VAD了，所以ASR这边不需要开VAD。经过多次尝试之后发现如果不加载VAD模型，即使加载了PT也无法转录标点

Code sample

self.model = AutoModel(model=model_name, device=device, disable_update=True, punc_model="ct-punc")

Expected behavior

Environment

OS (e.g., Linux): Windows
FunASR Version (e.g., 1.0.0): 1.1.6
ModelScope Version (e.g., 1.11.0):
PyTorch Version (e.g., 2.0.0):
How you installed funasr (pip, source):
Python version:
GPU (e.g., V100M32)
CUDA/cuDNN version (e.g., cuda11.7):
Docker version (e.g., funasr-runtime-sdk-cpu-0.4.1)
Any other relevant information:

LauraGPT commented 2 weeks ago

Yeah. But it is not a bug.