Open blackwingf opened 5 months ago
The dataset used for training and the pre-trained text encoder are trained on the English corpus and do not support inputs in other languages. The simple way to do this is to translate other language inputs into English.
用的是英文训练的模型,我在想,是不是可以参考TTS一样,也可以用拼音注解来训练呢?不知道和底模有没有关系。
python gen_wav.py --prompt "a bird chirps" --ddim_steps 100 --duration 10 --scale 3 --n_samples 1 --save_name "results"
when I change the prompt to Chinese, I found that it did not work