-
|
Hello, is it possible to generate the transcript and the translation at the same time via the CLI of Whisper, so that the VTT/SRT subtitle files (transcript and translation) have the identical segments and timecodes? |
Beta Was this translation helpful? Give feedback.
Replies: 1 comment
-
|
Not out-of-the-box, because the probability distribution of sampling timestamps will be different between the translation and transcription modes. It might be possible to hack a pipeline of transcribing with word timestamps and enforce the positions of the timestamp tokens in the translation mode (by editing |
Beta Was this translation helpful? Give feedback.
Not out-of-the-box, because the probability distribution of sampling timestamps will be different between the translation and transcription modes. It might be possible to hack a pipeline of transcribing with word timestamps and enforce the positions of the timestamp tokens in the translation mode (by editing
decoding.py), but it may be easier to just use a separate translation API at that point..