Become a sponsor to Tomoki Hayashi
I'm a postdoctoral researcher at Nagoya University in Japan. My research interests include speech synthesis, speech recognition, and environmental sound processing. I'm an author of ParallelWaveGAN and PytorchWaveNetVocoder, and the main developer of ESPnet.
By sponsoring, you will help me to make it possible to use a paid CI tool to accelerate the open-source development. It will also encourage me to improve my open-source software.
Featured work
-
espnet/espnet
End-to-End Speech Processing Toolkit
Python 8,610 -
kan-bayashi/ParallelWaveGAN
Unofficial Parallel WaveGAN (+ MelGAN & Multi-band MelGAN & HiFi-GAN & StyleMelGAN) with Pytorch
Jupyter Notebook 1,581 -
kan-bayashi/PytorchWaveNetVocoder
WaveNet-Vocoder implementation with pytorch.
Shell 298 -
kan-bayashi/LibriTTSLabel
Alignment files of LibriTTS.
-
kan-bayashi/VCTKCorpusFullContextLabel
Full context label for VCTK Corpus.