Whisper Vamp Plugin v1 #3
Merged
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
pierreguillot
force-pushed
the
dev/1.0.0
branch
from
5d547ed to
69fee10
Compare
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Outdated suggestions cannot be applied.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.
The first version of the speech-to-text Whisper Vamp plugin.
The Whisper Vamp plug-in is an implementation of the Whisper speech recognition model developed by OpenAI as a Vamp plug-in. The Whisper Vamp plug-in analyses the text in the audio stream and generates markers corresponding to the tokens (words and/or syllables) found.
The lightweight ggml-tiny model is embedded in the plugin (so you don’t have to download anything to start experimenting), but it is possible to download and use other models that may be more appropriate to your needs. You’ll find all the information in the user manual. Don’t hesitate to send me your feedback.
The plugin lets you define an input marker track to segment the analysis. This feature can be useful in avoiding the biases of certain models, such as the generation or repetition of words not present in the audio stream.