thu-ml / thu-ml/TurboDiffusion
Is this project support DiT based models about speech
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 3.7k
- Forks
- 277
- Avg merge
- 2h 57m
- Merged PRs (30d)
- 2
Description
There is some model on speech generation based on AdaLayerNorm Attention like f5-tts. Can it be supported on TurboDiffusion to speedup?
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing TurboDiffusion's existing model support and comparing it with the F5-TTS model linked in the issue, focusing on DiT, AdaLayerNorm, and attention requirements. A complete result would establish whether speech-generation models can be supported and define the scope of any required integration.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100