FunASR

FunASR copied to clipboard

wjyfelicity

KeyError: 'speaker-diarization-inference is not in the pipelines registry group speaker-diarization.

2

🐛 Bug when i run the code about-- quick_start_zh.md([FunASR](https://github.com/alibaba-damo-academy/FunASR/tree/main)/[docs](https://github.com/alibaba-damo-academy/FunASR/tree/main/docs)/[modelscope_pipeline](https://github.com/alibaba-damo-academy/FunASR/tree/main/docs/modelscope_pipeline) /quick_start_zh.md) from modelscope.pipelines import pipeline from modelscope.utils.constant import Tasks inference_diar_pipline = pipeline( mode="sond_demo", num_workers=0, task=Tasks.speaker_diarization, diar_model_config="sond.yaml", model='damo/speech_diarization_sond-en-us-callhome-8k-n16k4-pytorch', model_revision="v1.0.3", sv_model="damo/speech_xvector_sv-en-us-callhome-8k-spk6135-pytorch", sv_model_revision="v1.0.0", )...

san-kou7

where could I find some demo in nodejs

7

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） ## ❓ Questions and Help I can not find demo in funasr-samples, event in npm....

taoqf

question for told model

1

hi, thanks for your codes. I am trying to use model of "TOLD : A novel two-stage overlap-aware framework for Speaker Diarization", but cannot find the model(Found only eend-ola code)....

freshpearYoon

compute_audio_cmvn.py 脚本运行时 Segmentation fault

2

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 使用1.x版本funasr，跑aishell训练例子时，在stage 1 compute_audio_cmvn.py 步骤出现Segmentation fault ### To Reproduce Steps to reproduce the...

hicliff

Socket通信中pipeline执行speaker-verification任务出现choose a window size 400 that is [2, 0]报错

1

## 🐛 Bug 场景socket通信 ，API：pipelines，Task：'speaker-verification'的，方法：pipeline[wav1,wav2] ，报错：choose a window size 400 that is [2, 0] Debug不报错，RUN会报错。 方法拿出来单独测试就没问题。 ### To Reproduce Steps to reproduce the behavior (**always include the command you ran**):...

eugeneYz

我看代码里面还说的是目前不支持ngram，modelscope的模型卡页面也没有提供加挂LM的示例

JVfisher

在C++中读取token出错

1

https://github.com/alibaba-damo-academy/FunASR/blob/5e7eb6f160c48861cbcd39825a0cb98f98538772/runtime/onnxruntime/src/vocab.cpp#L29-L44 我是用的paraformer-zh-streaming模型，代码中在YAML文件中读取token，但是config.yaml中并没有token_list，执行函数会导致vocab为空，然后在 https://github.com/alibaba-damo-academy/FunASR/blob/5e7eb6f160c48861cbcd39825a0cb98f98538772/runtime/onnxruntime/src/vocab.cpp#L156 出错 token_list应该从token.json中读取

OgataAsatsuki

FunASR/runtime /csharp 将来会出自定义语音唤醒功能吗？

2

## ❓ Questions and Help 感谢开源和分享，让我们.NET csharp开发者也能轻松接入AI功能，现在通过： 1.[AliFsmnVad](https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/csharp/AliFsmnVad) 2.[AliParaformerAsr](https://github.com/alibaba-damo-academy/FunASR/tree/main/runtime/csharp/AliParaformerAsr) 实现了语音识别服务，准确率还不错，但是降噪效果和增益效果不够理想。 **请问csharp 将来会出自定义语音唤醒功能吗？如果有了语音唤醒+VAD+ASR+阿里云/百炼平台，就能实现chat语音助手功能了。** 希望将来，csharp 版本出一个高唤醒率，低功耗的自定义语音唤醒功能，**再次感谢开源和分享** ## 环境 - OS :windows10 x64 - FunASR Version :最新版本 - Microsoft.ML.OnnxRuntime :最终版本

Geek-Bob

[src/libmpg123/parse.c:wetwork():1365] error: Giving up resync after 1024 bytes

1

## ❓ Questions and Help #### The code runtime reported the following error Note: Illegal Audio-MPEG-Header 0x68746d6c at offset 584064. Note: Trying to resync... Note: Skipped 1024 bytes in input....

qianqianque163645546464