skinny.

Latest / Kana & Mari's SoundRepos (English)

AlexandaJerry/whisper-vits-japanese | Whisper powered Japanese VITS TTS | GitHub

Whisper-VITS-Japanese is a Python-based pipeline for training Japanese VITS text-to-speech models from long, unsegmented audio. It uses Whisper for transcription, converts SRT subtitles into timestamped datasets, automatically resamples and slices audio, generates VITS filelists, and supports both single-speaker and multi-speaker training with checkpoint recovery. Related: AlexandaJerry/whisper-vits-japanese / Whisper powered Japanese VITS TTS / GitHub

The skinny

The skinny isn't ready yet — notes appear once the transcript is processed.