[wav2vec 2.0] How to get char time information
Closed this issue · 3 comments
I am using this code for doing inference with wav2vec on an audio file. There is a discussion about it here.
The code works fine and I am able to get the transcription, but I was wondering if there was a way to get information on the times at which each character appears with respect to the audio duration, like some sort of synchronization.
Some ASR models output a matrix with char probabilities. Each column of the matrix corresponds to the inference done on some portion of audio, usually the window is very small.
Is it possible to get a similar output using wav2vec? How can I modify the code for doing this? Thanks a lot!
Hey, was any progress made on this?
This issue has been automatically marked as stale. If this issue is still affecting you, please leave any comment (for example, "bump"), and we'll keep it open. We are sorry that we haven't been able to prioritize it yet. If you have any new additional information, please include it with your comment!
Closing this issue after a prolonged period of inactivity. If this issue is still present in the latest release, please create a new issue with up-to-date information. Thank you!