Hi guys! Quick question, I need to voice clone, and I have 13k hours of ptbr speech (already as flac and edited). I need it for reading, not singing. What do you guys think is better: Titan+RVC2 or I’m better of just training it from 0? And would this setup give me a very close pitch? I’ve tested titan+rvc2 with 30 min dataset but I was not near close the voice, ~300 epochs 6 batches size, 32hz
#Voice clone for TTS
1 messages · Page 1 of 1 (latest)