bugbakery / bugbakery/transcribee
MLSS alignment model
Open
- Dominant language
- TypeScript
- Stars
- 515
- Forks
- 39
- Avg merge
- 19h 36m
- Merged PRs (30d)
- 15
Description
We curently use the wav2vec2 models. For the MLSS paper facebook trained a new universal alignment model that give better results, which we should switch to
Contributor guide
Research direction
No file, test, or entry point is named. Start by locating where wav2vec2 is configured or loaded, then determine how the MLSS universal alignment model would fit that path. Done means the replacement is integrated and its alignment results are verified against an existing evaluation or regression check.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- machine-learning, typescript
- Domain
- audio-video-rtc, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100