Hello, I have used LJspeech to train model , get a good result. But when I use biaobei dataset(a public chinese dataset) to train model , get a bad result(the generated result has meaningless content). my experiment's setup as following:
- reference "prepare_data.ipynb" to process the data, get the phone_seq and mel
- my dict is from fastspeech2' pinyin_dic
if you could give me some advice , I will very appreciate it ! Thank you!
Hello, I have used LJspeech to train model , get a good result. But when I use biaobei dataset(a public chinese dataset) to train model , get a bad result(the generated result has meaningless content). my experiment's setup as following:
if you could give me some advice , I will very appreciate it ! Thank you!