DiffSinger

DiffSinger copied to clipboard

I can't get checkpoint files.

4

According to README-SVS-opencpop-cascade.md, I made my own datasets and tried training. CUDA_VISIBLE_DEVICES=0 python tasks/run.py --config usr/configs/midi/cascade/mydatasets/aux_rel.yaml --exp_name MY_DATASETS_FS_EXP --reset The training went to Epoch 50 but I didn't any checkpoint...

nakasako

Hello, I have issue as I try to use another english dataset. And I'm wondering why Inference from packed test set can work (`CUDA_VISIBLE_DEVICES=0 python tasks/run.py --config usr/configs/midi/e2e/opencpop/ds100_adj_rel.yaml --exp_name $MY_DS_EXP_NAME --reset --infer`) but inference model from raw input (`python inference/svs/ds_e2e.py --config usr/configs/midi/e2e/opencpop/ds100_adj_rel.yaml --exp_name $MY_DS_EXP_NAME`) needs same phoneme set size?

14

Hello, I have issue as I try to use another english dataset. And I'm wondering why Inference from packed test set can work (`CUDA_VISIBLE_DEVICES=0 python tasks/run.py --config usr/configs/midi/e2e/opencpop/ds100_adj_rel.yaml --exp_name $MY_DS_EXP_NAME...

michaellin99999

custom phone_set file

1

Hi, with data preview we have create 72 phonemes, is there a way to train the model such that it doesn't use the existing phone_set file with 62 phonemes and...

michaellin99999

In the e2e trainning mode of opencpop, skip_decoder is true and the decoder part is not trainned at all, right? But in the inference, you still use run_decoder to get...

Liujingxiu23

hello，is there 22050 sample rate feature trained hifigan models for svs? thanks

11721206

custom training data split

2

hello. Thanks for sharing your great research! I'm going to do an experiment to see the effect of data size on diffsinger model training. So, I want to train using...

juheo

Hi, @MoonInTheRiver, thank you for your great work. I have some questions about the training of vocoder as follows: 1. In the training phase, did you use the same loss...

LqNoob

HuggingFace -> Hugging Face

eltociear

下载ZIP之后显示无法打开，请问有知道的大佬吗？

2

liulian233-23

AttributeError: 'LatestModelCheckpoint' object has no attribute '_save_model'

1

 When I train FFT-Singer from scratch, An AttributeError occur. How do I solve this problem? Thanks.

hsk-yjk