NTT123's repositories
light-speed
A modified VITS that utilizes phoneme duration's ground truth for better robustness
Vietnamese-Text-To-Speech-Dataset
A synthesized dataset for Vietnamese TTS task
hifigan-tpu
Train HiFi-GAN on TPU
sketch-transformer
Modeling Draw, Quick! dataset using transformers
soft-dtw-jax
Soft-DTW loss in JAX
wavernn-16bit
The (unofficial) vanilla version of WaveRNN
wavegru-vocoder
WaveGRU vocoder
pointer-networks
An unofficial implementation of pointer networks.
fast_wavegru
Fast C++ WaveGRU
haiku_trainer
A helper library for training dm-haiku models.
simple-hifigan
Another HiFiGAN implementation using PyTorch
ai-notebooks
My collection of Jupyter notebooks on AI
cat-diffusion
Diffusion models in JAX
llama
Open weights LLM from Meta
Language:Jupyter NotebookApache-2.0000
tiny-neural-rendering
a simple neural rendering library
MIT000
viet-aligner
Aligner vietnamese text and audio clip
Language:PythonMIT000