Add language_bias parameter to detect_language #2004
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Outdated suggestions cannot be applied.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.
We are doing a lot of multi-lingual transcriptions, especially with language learners. We have found that Whisper will often incorrectly identify the language when a language learner is speaking their target language.
For example, a native Korean speaker will speak English, but with a strong Korean accent, and Whisper will identify the language as Korean, not English.
We've found that adding a language bias of +1.0 to the language learner's target language is enough to nudge whisper in the direction of the user's target language, while still allowing it to properly identify the user's native language, and other languages.