Айдос Сарсембаев comments

Results 5 comments of


                                            Айдос Сарсембаев

Is there any research about appropriate size of dataset for Fastspeech2?

+++ I'm also interested

Retraining the model with 16k sampling rate data

> Changing that single line in `preprocessor/preprocessor.py` fixed this issue for me, training with 16 kHz audio. Thanks for the pointer! thank you so much! I completely forgot that librosa...

New parameters for sampling_rate=44.1 kHz

Hi! I think that a bigger concern for you would be not the SR of the FastSpeech2 model, but rather the vocoder. Because, other than tuning configs and further training...

optimizer and scheduler

> Hi, why do you update learning rate before optimizer.step() in [code](https://github.com/ming024/FastSpeech2/blob/master/model/optimizer.py#L22-L24)? Should not we conduct optimizer.step() fist and then conduct scheduler.step()? Or is there some other consideration? Hi! Have...

model cantnot fit to data, and test voice is too bad when i use the paper configuration

> I hava tried that configuration but the result is terrible.There are many noises and wrong pronounciation within the audio while in the inference,but the audio synthesized of validation in...