Tomoki Hayashi
kan-bayashi
Main developer of ESPnet / COO @ Human Dataware Lab. Co., Ltd. / Postdoctoral researcher @ Nagoya University
Languages
Top Repositories
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
WaveNet-Vocoder implementation with pytorch.
Alignment files of LibriTTS.
Interspeech 2019 tutorial materials
WaveNet Vocoder Samples
a MUSHRA compliant web audio API based experiment software
Repositories
40Alignment files of LibriTTS.
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
My dotfiles (ghostty + tmux + neovim)
No description provided.
STIV - Simple Terminal Image Viewer
Jellybeans inspired Neovim color scheme
WaveNet Vocoder Samples
Interspeech 2019 tutorial materials
WaveNet-Vocoder implementation with pytorch.
Your agent in your terminal, equipped with local tools: writes code, uses the terminal, browses the web, vision.
Full context label for VCTK Corpus.
No description provided.
a MUSHRA compliant web audio API based experiment software
No description provided.
Tacotron2 with BERT examples
Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
End-to-End Speech Processing Toolkit
A neural network training interface based on PyTorch, with a focus on flexibility
OneShot Learning-based hotword detection.
Onnx wrapper for espnet infrernce model
Audio samples
VideoX: a collection of video cross-modal models
Non-autoregressive sequence-to-sequence voice conversion
No description provided.
Tensors and Dynamic neural networks in Python with strong GPU acceleration
Demo HP for DiscreTalk.
ESPnet2解説原稿付録
Phoneme alignment for JSSS corpus
Non-parallel Voice Conversion
No description provided.