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
6.17k stars 657 forks source link

paraformer-en识别结果存在问题 #1941

Open RussZhang opened 2 months ago

RussZhang commented 2 months 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-en识别结果完全不对,可能是词表存在问题。如下图所示,识别结果中出现de等非英文字符。 image

已按如下步骤更新过funasr,还是存在这一问题。 image

若是词表存在问题,tokens.json好像是在模型文件中,是否应该更新paraformer-en模型的版本?

To Reproduce

Steps to reproduce the behavior (always include the command you ran): image

  1. Run python test_paraformer.py

Environment

Avatar4689 commented 2 months ago

遇到了同样的问题

xipingL commented 1 month ago

你好请问解决了吗? 我也遇到了同样的问题

RussZhang commented 1 month ago

你好请问解决了吗? 我也遇到了同样的问题

并没有,你可以在他们的钉钉群再催一下

treya-lin commented 2 weeks ago

我也遇到了这个问题 好诡异