Compressing Kokoro-82M: Most of the Decoder Can Go, Its Last Layer Cannot

Sat, 07 Nov 2026 14:00:00 +0300

Kokoro-82M is a small, good-sounding English text-to-speech model with 28 voices. Two thirds of its 81.8 million parameters sit in one place: the decoder that turns an internal description of speech into a waveform. I wanted a smaller, faster decoder that a listener could not tell apart from the original, while keeping everything else about Kokoro (pronunciation, timing, intonation, the voices) exactly as it is.

Kokoro on DRM HSE

Compressing Kokoro-82M: Most of the Decoder Can Go, Its Last Layer Cannot