drakirus

Would it make sense to rather compare distances to sub words rather instead full words ? I don't know if this would be possible because now you have to deal with sequence modeling to transform audio to sub words to words to sentences.

I'd be curious to see the WER on out of vocabulary words, seems like this cannot generalize to unseen word's given this step: 'The closest of ~229,000 English words wins, and the slices become a transcript'

OmniVoice is a state-of-the-art zero-shot multilingual TTS model supporting more than 600 languages. Built on a novel diffusion language model architecture, it generates high-quality speech with superior inference speed, supporting voice cloning and voice design.