search

tomchang25 / whisper-auto-transcribe

Auto transcribe tool based on whisper
MIT License
205 stars 14 forks source link

Stable whisper throw error in extremly long audio #41

Closed tomchang25 closed 1 year ago

tomchang25 commented 1 year ago

Track this issue now, but I don't think it will be resolved in the near future. As an alternative solution, you can either change the model or slice your file.

It appears that one hour is a dividing line.

Edit: I have found where the problem is. Setting the language to 'auto' may cause the model to incorrectly identify the language, resulting in errors. In my case, both two different language audio incorrectly identify as Welish:

English -> Welish Japanese-> Welish

Setting the language explicitly should solve this problem.

tomchang25 commented 1 year ago

Should fix in the latest version of Stable whisper.