18:25
2026-06-28
discuss.huggingface.co
machine-learning
HoLo-ToLk: tokenizer-free speech (STT + TTS) on the 0-parameter HSL byte substrate
Researcher HoLo-ToLk built speech-to-text and text-to-speech models using a tokenizer-free byte substrate, achieving a character error rate of 0.194 on STT, beating a mel-spectrogram baseline, while T…