StarGAN-Voice-Conversion

StarGAN-Voice-Conversion copied to clipboard

Ha0Tang

I use tensorflow-gpu. will the training physe be done on gpu instead of cpu?

talka1

does the model get checkpoints and can you resume training at a later stage?

talka1

ValueError: Object arrays cannot be loaded when allow_pickle=False

4

> [485:486]svaing file: ./data/processed/TM1-100131_0.npy > [485:486]svaing file: ./data/processed/TM1-100131_512.npy > save file: ./data/processed/TM1-100132 > audio mcep shape (36, 512) > [486:486]svaing file: ./data/processed/TM1-100132_0.npy > Traceback (most recent call last): > File...

salisbury-espinosa

Converted samples are corrupted!

2

in the samples folder, files that are the converted speech won't open with any player, I even tried out my phone to play but it didn't work.

BenRafatian

hey, I have tested this repository on my ubuntu system and solved the issues of dependencies like librosa, for solving librosa issues I used the SoundFile library for using the...

bhaskarkumar1

wavs generated by convert.py are just noise

3

Does anybody have the same problem? I use the laest code, no parameter changed. @hujinsen the wavs in "converted_speech" can not be played, could you share some result wavs that...

Liujingxiu23

can this model train VCTK dataset?

crashcar

not able to reproduce the results in original paper

6

I cannot reproduce the results in original paper. I used tensorflow 1.8.0.

NOrangeeroli