phonemization

标签

Cards List
#phonemization

FastThaiG2P: Lightning-fast Thai Grapheme-to-phoneme Conversion for Voice Agent Pipelines

arXiv cs.CL · 2026-08-14 缓存

This paper presents FastThaiG2P, a sub-millisecond Thai grapheme-to-phoneme conversion tool for TTS pipelines, achieving 0.15 ms average latency on a 27k-utterance benchmark. The authors demonstrate it by training a StyleTTS 2 Thai TTS model on a phonemized 20-hour open dataset.

0 人收藏 0 人点赞
← 返回首页

提交意见反馈