Fix Whisper doc + improve max_decode_ratio#1858
Merged
anautsch merged 9 commits intospeechbrain:developfrom Feb 22, 2023
Merged
Fix Whisper doc + improve max_decode_ratio#1858anautsch merged 9 commits intospeechbrain:developfrom
anautsch merged 9 commits intospeechbrain:developfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
max_decode_ratiothat is not taking into account the maximum tokens length of the Whisper decoder. Now, we can dynamically change the upper bound by changing thechange_max_decoding_lengthfunction.I checked, and everything works as expected. I was able in zero shot to get 2.44 CER, 6.4 WER on Test Clean and test CER: 6.74, test WER: 14.31 with
max_decode_ratio=1.0.I used the beautiful test recipe made by Andreas on CommonVoice/LibriSpeech and all checks passed.
(we need to fix this for the 0.5.14/0.6)