FunASR

FunASR copied to clipboard

Fsmn_vad参数speech_to_sil_time_thres

1

## ❓ Questions and Help 为啥speech_to_sil_time_thres设置的越大，切割出的音频会越多呢？

tesfayetong

whisper-larger-v3模型，识别结果没有时间戳，10min音频

1

10分钟的音频 依然没有时间戳 模型；whisper-large-v3 ## ❓ Questions and Help from funasr import AutoModel model = AutoModel( model="iic/Whisper-large-v3", vad_model="iic/speech_fsmn_vad_zh-cn-16k-common-pytorch", vad_kwargs={"max_single_segment_time": 30000}, ) DecodingOptions = { "task": "transcribe", "language": None, "without_timestamps": False, }...

ExpressGit

model_blade.torchscript do not exists

7

使用docker部署离线gpu funasr，使用原始的paraformer-zh后会自动下载相应的模型，生成model_blade.torchscript文件，但是我换成SenseVoiceSmall后不下载，也不生成model_blade.torchscript文件，报错 /workspace/models/damo/SenseVoiceSmall/model_blade.torchscript do not exists。求指导下怎么生成这个文件？

dwyane20

自己编译各种问题，花了1天时间，好不容易编译通过后，运行出错

tiandiweizun

docker安装后,本地调用asr服务连不上.

3

本地根据官网文档docker run 起来之后,跑了脚本. ``` bash run_server.sh --download-model-dir /workspace/models --vad-dir damo/speech_fsmn_vad_zh-cn-16k-common-onnx --model-dir damo/speech_paraformer-large-vad-punc_asr_nat-zh-cn-16k-common-vocab8404-pytorch --punc-dir damo/punc_ct-transformer_cn-en-common-vocab471067-large-onnx --lm-dir damo/speech_ngram_lm_zh-cn-ai-wesp-fst --itn-dir thuduj12/fst_itn_zh --hotword /workspace/models/hotwords.txt --certfile 0 ```  但是我本级打开使用html client 连接asr server 显示连接不上. telnet...

V-yw

raceback (most recent call last): | 0/4 [00:00

sethws

初见遇到的datasets的版本问题

8

刚开始用FUNASR, 一上来配置环境就卡住了。 在安装完modelscope之后， File "time_prodict.py", line 9, in from modelscope.pipelines import pipeline File "/usr/local/anaconda3/envs/lbs_py38/lib/python3.8/site-packages/modelscope/pipelines/__init__.py", line 4, in from .base import Pipeline File "/usr/local/anaconda3/envs/lbs_py38/lib/python3.8/site-packages/modelscope/pipelines/base.py", line 16, in from modelscope.msdatasets import MsDataset...

xiaochunxin

paraformer onnx-gpu 转 tensorrt 报错 (Could not find any implementation for node)

3

# 1. environment - OS (e.g., Linux): Linux - FunASR Version (e.g., 1.0.0): 1.1.3 - ModelScope Version (e.g., 1.11.0): 1.11.0 - GPU (e.g., V100M32): A100 - ## 1.1 pt to...

willnufe

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 funasr-runtime-sdk-gpu-0.1.1镜像部署的服务，存在内存泄露问题 ### To Reproduce Steps to reproduce the behavior (**always include the...

zane5566

1.C++的funasr-onnx-offline-sv.cpp和funasr-onnx-2pass.cpp完成； 2.C++ 内存泄漏测试：测试过2小时的音频ok； 3.python导出onnx模型和demo示例代码完成； 4.python/onnx的demo和C++/onnx推理结果已对齐； 5.python pytorch 推理demo和python onnx demo结果已对齐；

apple2333cream