kan-bayashi

ParallelWaveGAN

Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch

PytorchWaveNetVocoder

WaveNet-Vocoder implementation with pytorch.

LibriTTSLabel

Alignment files of LibriTTS.

INTERSPEECH19_TUTORIAL

Interspeech 2019 tutorial materials

WaveNetVocoderSamples

WaveNet Vocoder Samples

webMUSHRA

a MUSHRA compliant web audio API based experiment software

espnet

End-to-End Speech Processing Toolkit

dotfiles

My dotfiles (zsh + tmux 2.6 + vim 8 / nvim)

NonARSeq2SeqVC

Non-autoregressive sequence-to-sequence voice conversion

icassp2022-streaming-vc

asj-espnet2-tutorial

ESPnet2解説原稿付録

VCTKCorpusFullContextLabel

Full context label for VCTK Corpus.

kan-bayashi.github.io

AudioSamples

Audio samples

crank

Non-parallel Voice Conversion

denite.nvim

:dragon: Dark powered asynchronous unite all interfaces for Neovim/Vim8

DiscreTalk

Demo HP for DiscreTalk.

EfficientWord-Net

OneShot Learning-based hotword detection.

espnet_onnx

Onnx wrapper for espnet infrernce model

fonts

interspeech2019-tutorial

INTERSPEECH 2019 Tutorial Materials

JSSSLabel

Phoneme alignment for JSSS corpus

litellm

Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)

nvim-jellybeans

Jellybeans inspired Neovim color scheme

pytorch

Tensors and Dynamic neural networks in Python with strong GPU acceleration

sprocket

Voice Conversion Tool Kit

themes

torchpack

A neural network training interface based on PyTorch, with a focus on flexibility

trt-lightnet

VideoX

VideoX: a collection of video cross-modal models