When I use Chinese input speech and Chinese reference speech for conversion, the output sounds like a foreigner speaking Chinese, and the intonation is incorrect. Even after retraining the model using a Chinese dataset, the problem persists. How can I resolve this?
When I use Chinese input speech and Chinese reference speech for conversion, the output sounds like a foreigner speaking Chinese, and the intonation is incorrect. Even after retraining the model using a Chinese dataset, the problem persists. How can I resolve this?