TuananhCR/Dia-Finetuning-Vietnamese
TTS Dia finetuning for Vietnamese
Builds on Nari Labs' DIA 1.6B model with fine-tuning for 44.1 kHz Vietnamese speech synthesis, supporting multi-speaker regional accents (North/South, male/female) and style control via temperature, top_p, and cfg_scale parameters. Leverages torch.compile and bfloat16 optimization for inference speed, with a Gradio interface for interactive generation using speaker tags to switch voices mid-utterance.
125 stars.
Stars
125
Forks
38
Language
Python
License
Apache-2.0
Category
Last pushed
Dec 03, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/voice-ai/TuananhCR/Dia-Finetuning-Vietnamese"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related tools
thinhlpg/vixtts-demo
A Vietnamese Voice Cloning Text-to-Speech Model ✨
dangvansam/viet-tts
VietTTS: An Open-Source Vietnamese Text to Speech
NTT123/vietTTS
Vietnamese Text to Speech library
ekwek1/soprano-factory
Soprano-Factory: Train your own 2000x realtime text-to-speech model
modelscope/KAN-TTS
KAN-TTS is a speech-synthesis training framework, please try the demos we have posted at ...