DiffSinger

DiffSinger copied to clipboard

How to train another language?

4

I think this "DiffSinger" model is based on Chinese. Please give me advice on how to train them in another language. Thank you for share!

Cardroid

Thank you for releasing the POPCS dataset, I was wondering the phoneme duration label is automatically labeled by MFA tool or labeled by human?

YawYoung

multi speaker sing

1

By enable the "with_spk_embed" option, and then retaining the model, can it support multi speaker singing?

newportchen

How to do the DiffSinge test, why does my program report no errors but no audio files are generated?

2

How to do the DiffSinge test, why does my program report no errors but no audio files are generated?

baixinping618

Hi, I noticed that different versions of parselmouth would result in different length of the computed f0. This is also mentioned in the comment of your code. https://github.com/MoonInTheRiver/DiffSinger/blob/ae3e8f05e04ea28bd6d68ff8eb2a6ae882f7d9c0/data_gen/tts/data_gen_utils.py#L176 I think...

yuxinyuan

Thank you very much for providing PopCS for free~! When I reading your paper, I noticed you `re-trained a Montreal Forced Aligner tool` to build the dataset PopCS. Would you...

YawYoung

How to inference on other <midi, text> files using the opencpop phone_set.json?

4

Hi, thanks for the great work! I want to inference on my own files. I generated the corresponding meta.json and tried to binarize it. But the binarizer can only generate...

SkyAndCloud

How to train HifiGAN-Singing from scratch?

3

Could you please give some instructions? Thank you very much

Charlottecuc

How to train a model from scratch, with new data set?

3

The training steps given in the readme.md for DiffSinger require your saved checkpoints and your training data. Can you please indicate how train a model from scratch, with a new...

duheyu

please be patient when applying for datasets :)

6

I will give you the link within seven days. If not, email me again.

MoonInTheRiver