thu-ml / thu-ml/TurboDiffusion

Is this project support DiT based models about speech

Open
#48 0 comments 0 reactions 0 assignees View on GitHub

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

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. 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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.