Add parameter maxLength to transcribe #3703
Merged
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Outdated suggestions cannot be applied.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.
Fixes #3688
This PR adds the possibility to configure the
max-length
parameter that is passed to whisper.cpp (previously hard coded to 1).The function
transcribe
now also accepts a parametermaxLength
.The parameter can only be also be set to null, to use
whisper.cpp
's default token grouping (useful for generating a movie-style transcription).Backwards compatibility
The function is backward compatible. If
maxLength
is not provided, a default value of 1 is used (same behaviour as before)Note
Since
convertToCaptions
groups the transcription-items and not the tokens, the parametermaxLength
can now only be used whentokenLevelTimestamps
is set false.Question: Would
tokensPerTranscriptionItem
be a batter/more accurate name?/claim 3688