04:04
2026-07-25
promptcube3.com
artificial-intelligence
Inflect v2: Running TTS under 10M Parameters
Inflect v2, a text-to-speech model under 10 million parameters, achieves competitive performance with 4.395 UTMOS22 and 3.99% semantic WER for the Micro version (9.36M parameters) and 4.386 UTMOS22 wi…