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
6.48k stars 688 forks source link

英文微调后输出字符没有用空格隔开 #1399

Closed tuocheng0824 closed 6 months ago

tuocheng0824 commented 7 months ago

微调英文模型 speech_paraformer_asr-en-16k-vocab4199-pytorch 我微调后生成的英文 如下所示,有些英文是没有空格隔开: we're heretohelp ifyou have questionsabout anexisting orrder

LauraGPT commented 7 months ago

May be you could debug it in https://github.com/alibaba-damo-academy/FunASR/blob/main/funasr/models/paraformer/model.py#L535

LauraGPT commented 6 months ago

Sorry, it is a bug. Please ref to https://github.com/alibaba-damo-academy/FunASR/issues/1463