Open ab-pandey opened 1 year ago
guillaumekln
commented
1 year ago Since I am new to Ctranslate2, I am having difficulty in cloning https://github.com/openai/whisper/pull/676 to faster_whisper. Can someone help me on this? Thanks
What have you tried so far? Maybe you can share your current changes and we can help you implement this.
ab-pandey
commented
1 year ago Actually I am not able to figure out how to proceed further. There are several variables in the fix like "content_frames", "N_FRAMES", "segment"; functions used "pad_or_trim" in this solution which I am not able to figure out how to get the correct values for faster_whisper implementation
elloza
commented
6 months ago has been this implemented?
dilerbatu
commented
6 months ago Any update ?
trungkienbkhn
commented
6 months ago FYI, I created a new PR to implement this feature: https://github.com/SYSTRAN/faster-whisper/pull/732
ldolegowski92
commented
3 months ago Do Twojej wiadomości, utworzyłem nowy PR, aby wdrożyć tę funkcję: #732
How will the model behave if the conditions are not met?
Since wishper detects language based on first 30 secs of the audio, sometimes there are errors in language detection. For example This video is in english but both whisper and faster_whisper detects language as hindi "hi". There is a solution for this issue in whisper here. Since I am new to Ctranslate2, I am having difficulty in cloning this solution to faster_whisper. Can someone help me on this? Thanks. P.S. I have tested the solution in whisper and it works.