diodiogod-TTS-Audio-Suite

Files

T

History

diodiogod 829b0aed81 Fix F5-TTS bundled integration and ChatterBox model detection

- Bundle F5-TTS source code to resolve numpy dependency conflicts
- Fix all import paths to use bundled engines.f5_tts package
- Update ChatterBox model detection to properly scan language subdirectories
- Fix missing return statement in F5-TTS engine instantiation
- Add missing sys import in Higgs Audio downloader
- Update requirements.txt with bundled F5-TTS approach

2025-08-19 00:06:50 -03:00

dit.py

Fix F5-TTS bundled integration and ChatterBox model detection

2025-08-19 00:06:50 -03:00

mmdit.py

Fix F5-TTS bundled integration and ChatterBox model detection

2025-08-19 00:06:50 -03:00

README.md

Fix F5-TTS bundled integration and ChatterBox model detection

2025-08-19 00:06:50 -03:00

unett.py

Fix F5-TTS bundled integration and ChatterBox model detection

2025-08-19 00:06:50 -03:00

README.md

Backbones quick introduction

unett.py

flat unet transformer
structure same as in e2-tts & voicebox paper except using rotary pos emb
possible abs pos emb & convnextv2 blocks for embedded text before concat

dit.py

adaln-zero dit
embedded timestep as condition
concatted noised_input + masked_cond + embedded_text, linear proj in
possible abs pos emb & convnextv2 blocks for embedded text before concat
possible long skip connection (first layer to last layer)

mmdit.py

stable diffusion 3 block structure
timestep as condition
left stream: text embedded and applied a abs pos emb
right stream: masked_cond & noised_input concatted and with same conv pos emb as unett