Dev compresses Hindi & Telugu TTS model to under 100KB via int8 quantization

kingslyj · x · 2026-11-19

Developer @nutanc quantized weights to int8 to shrink a Hindi and Telugu TTS model first below 1MB, then to under 100KB.

He admits the 100KB version sounds worse than the 1MB one, but calls it absolutely usable — a notable datapoint for on-device speech deployment at extreme sizes.

Original post →

More from Multimodal

Multimodal channel →