i have a question about TTS? (Very stupid question)
Instead of training it with talking, could you train it with music?
No, not from Meta but as a general guide, no TTS or text-to-speech model is compatible with music. You can't turn text to music, however you can turn notes to music, but those use different models whereas TTS or text to speech works to extract features from text like syllables and other language features, and aligns them to waveforms that produce the sound or speech. Hope this helps :)
No, not from Meta but as a general guide, no TTS or text-to-speech model is compatible with music. You can't turn text to music, however you can turn notes to music, but those use different models whereas TTS or text to speech works to extract features from text like syllables and other language features, and aligns them to waveforms that produce the sound or speech. Hope this helps :)
Sorry, this was a stupid idea I had at one point I already answered it