feat(Whisper-alfa): Add Whisper processor #399
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
n0th1ng-else
force-pushed
the
offline
branch
6 times, most recently
from
e3631e5
to
ce5d841
Compare
In this commit we establish the early version of the Whisper processor. We need to check how to run it safely so it does not kill the process, we also need to estimate the memory consumption is well below under the limits of our low-resource availability model. Not to mention we want to probably have a Whisper as a singleton and we need to somehow download the recognition model - it take a lot of space so we can not just store it in the repository We do not enable Whisper as of now due to the challenges mentioned above, But we also change the way we transform the voice file. Instead of prism-media we use fluent-ffmpeg and we now always dump the wav file into the file system as well. This is the requirement for the Whisper model but I also want to unify the interface and stop having different processing flows for audio and video. This change will be enabled with the release
n0th1ng-else
force-pushed
the
offline
branch
from
ce5d841
to
88072c1
Compare
|
|
🎉 This PR is included in version 4.30.0 🎉 The release is available on GitHub release Your semantic-release bot 📦🚀 |
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Outdated suggestions cannot be applied.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.
In this commit we establish the early version of the Whisper processor. We need to check how to run it safely so it does not kill the process, we also need to estimate the memory consumption is well below under the limits of our low-resource availability model. Not to mention we want to probably have a Whisper as a singleton and we need to somehow download the recognition model - it take a lot of space so we can not just store it in the repository
We do not enable Whisper as of now due to the challenges mentioned above, But we also change the way we transform the voice file. Instead of prism-media we use fluent-ffmpeg and we now always dump the wav file into the file system as well. This is the requirement for the Whisper model but I also want to unify the interface and stop having different processing flows for audio and video. This change will be enabled with the release