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

6.99k stars 744 forks source link

当我通过run_server.sh使用SenseVoiceSmall模型时出现错误:models/iic/SenseVoiceSmall/model_quant.onnx do not exists. #2035

Closed firekirin67 closed 1 month ago

firekirin67 commented 2 months ago

❓ Questions and Help

当我通过run_server.sh使用SenseVoiceSmall模型时出现错误

提示错误信息:models/iic/SenseVoiceSmall/model_quant.onnx do not exists.

What is your question?

Code

通过在run_server.sh文件修改脚本代码如下:

model_dir="damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-onnx"

model_dir="iic/SenseVoiceSmall"

vad_dir="damo/speech_fsmn_vad_zh-cn-16k-common-onnx"

vad_dir=""

punc_dir="damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx"

punv_dir=""

itn_dir="thuduj12/fst_itn_zh"

itn_dir=""

lm_dir="damo/speech_ngram_lm_zh-cn-ai-wesp-fst"

What have you tried?

What's your environment?

OS (e.g., Linux): Linux
FunASR Version (e.g., 1.1.6):1.1.6
ModelScope Version (e.g., 1.11.0):1.11.0
PyTorch Version (e.g., 2.0.0):8.32
How you installed funasr (pip, source): source
Python version:3.1.16

lyblsgo commented 1 month ago

已支持SensevoiceSmall，部署参考https://github.com/modelscope/FunASR/blob/main/runtime/docs/SDK_advanced_guide_offline_zh.md