Pinned Repositories
DeepFilterNet
Noise supression using deep filtering
espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
indo_text_processor
Utility for Text Normalisation or Inverse Normalisation
LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
lyric-alignment
Vietnamese song lyric alignment framework
MagicAnimateHandson
NeurIPS-llm-efficiency-challenge
Code for NeurIPS LLM Efficiency Challenge
sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
SHOW
This is the codebase for SHOW in Generating Holistic 3D Human Motion from Speech [CVPR2023],
vi_kaldi-montreal
Vietnamese voice2json profile based on Kaldi
toanhvu2's Repositories
toanhvu2/DeepFilterNet
Noise supression using deep filtering
toanhvu2/espeak-ng
eSpeak NG is an open source speech synthesizer that supports more than hundred languages and accents.
toanhvu2/indo_text_processor
Utility for Text Normalisation or Inverse Normalisation
toanhvu2/LLMs-from-scratch
Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step
toanhvu2/lyric-alignment
Vietnamese song lyric alignment framework
toanhvu2/MagicAnimateHandson
toanhvu2/NeurIPS-llm-efficiency-challenge
Code for NeurIPS LLM Efficiency Challenge
toanhvu2/sentencepiece
Unsupervised text tokenizer for Neural Network-based text generation.
toanhvu2/SHOW
This is the codebase for SHOW in Generating Holistic 3D Human Motion from Speech [CVPR2023],
toanhvu2/vi_kaldi-montreal
Vietnamese voice2json profile based on Kaldi
toanhvu2/VietnameseTextNormalizer
Thư viện chuẩn hóa văn bản Tiếng Việt
toanhvu2/Vinorm
Python - NSW package for Vietnamese: Normalization system to convert numbers, abbreviations, and words that cannot be pronounced into syllables
toanhvu2/visen
ViSen is library to format tone of Vietnamese sentences
toanhvu2/ViSV2TTS
Vietnamese Voice Cloning System using Speaker Verification training on multispeaker VITS
toanhvu2/WebGPT
Run GPT model on the browser with WebGPU. An implementation of GPT inference in less than ~1500 lines of vanilla Javascript.
toanhvu2/voice-converter
Module for freely modifying or controlling voice