MahmoudAshraf97 / whisper-diarization

Automatic Speech Recognition with Speaker Diarization based on OpenAI Whisper
BSD 2-Clause "Simplified" License
2.44k stars 238 forks source link

Language param not working #171

Open alexauvray opened 3 months ago

alexauvray commented 3 months ago

My audio is in French. I tried to specify --language fr but the transcript is still translated in English.

Same thing happens when I don't use the language param.

Thamos commented 3 months ago

Did you specify the model? Default model is "medium.en".2

MahmoudAshraf97 commented 2 months ago

you need to specify a model that is multilingual