Bugfix: Illogical "Avoid computing higher temperatures on no_speech" #625
Conversation
This file contains 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
Fixing: #621 Regression since PR: #225 **The bug**: It's "silence" when decoding has failed due to `compression_ratio_threshold` [+no_speech_threshold] in #225, when further down the code it's not "silence" anymore. "Silence" should be only when decoding has failed due to `log_prob_threshold` [+no_speech_threshold].
joiemoie
added a commit
to joiemoie/faster-whisper
that referenced
this pull request
Jan 19, 2024
|
@Purfview any reason you decided to close this issue? i am using your patch and it's improving the output result |
|
Thanks @Purfview for the fix, this explanation makes sens for me. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Fixing: #621
Regression since PR: #225
The bug: It's "silence" when decoding has failed due to
compression_ratio_threshold[+no_speech_threshold] in #225, when further down the code it's not "silence" anymore."Silence" should be only when decoding has failed due to
log_prob_threshold[+no_speech_threshold].As described there:
faster-whisper/faster_whisper/transcribe.py
Lines 239 to 241 in 44f7e58
The bug opens the gates for the hallucination loops.