2026-11-15 · America/Los_Angeles · 行业新闻 · #4
Show HN: Nano-Edge-TTS – 70x realtime, Lightweight Kokoro-based TTS model
A 1.75M-parameter decoder for Kokoro-82M that runs no neural network at audio rate. Kokoro's text side (pronunciation, timing, pitch and all voices) is unchanged. Its 53.3M-parameter waveform decoder is replaced by two small networks that run 80 and 160 times a second and set per-frequency gains on a pulse train and on white noise. Two inverse STFTs turn the result into audio. Paper: No Network at Audio Rate: A 1.75M-Parameter Harmonic-plus-Noise Decoder for Kokoro-82M (method, results, listening tests and negative results). ¹ 240 validation sentences, PyTorch, Apple M4. ² Six validation sente
热度 29.1 / 100;排名与评分保留该期记录。