Katsuya Iida

Voice100 includes neural TTS/ASR models. Inference of Voice100 is low cost as its models are tiny and only depend on CNN without autoregression.

kaiidams

A public domain single speaker Japanese speech dataset

kaiidams

Unofficial SoundStream implementation of Pytorch with training code and 16kHz pretrained checkpoint

kaiidams

Text-to-speech and speech recognition, VAD with NVIDIA NeMo and ONNX Runtime for .NET Core.

kaiidams