Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Implementation of batched whisper and updates on Audio pipeline #53

Merged
merged 91 commits into from
Mar 16, 2024

Conversation

Jiltseb
Copy link
Contributor

@Jiltseb Jiltseb commented Feb 14, 2024

This PR is a new feature mentioned in #41 It integrates faster version of ASR to Aana SDK. The PR also creates Audio dataclass for type handling in audio pipelines.

Components:

  1. Vad deployment and related scripts.
  2. Updated whisper deployment and related scripts.
  3. Updated pipelines, endpoints.
  4. Audio dataclass creation, file handling and execution throughout the pipeline.
  5. Tests audio data class, extract_audio method, vad and whisper deployments, integration tests for batched whisper

@Jiltseb
Copy link
Contributor Author

Jiltseb commented Mar 12, 2024

Added the changes after @movchan74 review. Please resolve the comments if the issues are addressed and point out unaddressed ones, if any.

aana/utils/general.py Outdated Show resolved Hide resolved
aana/utils/general.py Outdated Show resolved Hide resolved
aana/utils/general.py Outdated Show resolved Hide resolved
aana/utils/video.py Outdated Show resolved Hide resolved
@movchan74 movchan74 requested a review from evanderiel March 15, 2024 14:57
@Jiltseb Jiltseb merged commit 6f4be69 into main Mar 16, 2024
2 checks passed
@movchan74 movchan74 deleted the js/batched_whisper branch June 28, 2024 08:50
movchan74 pushed a commit that referenced this pull request Sep 19, 2024
Implementation of batched whisper and updates on Audio pipeline
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
3 participants