Retrieval-based-Voice-Conversion-WebUI icon indicating copy to clipboard operation
Retrieval-based-Voice-Conversion-WebUI copied to clipboard

Train Model not doing anything?

Open Mugen-CC opened this issue 2 years ago • 1 comments

When I click Train Model, these lines appear on the cmd

write filelist done
use gpus:
python train_nsf_sim_cache_sid_load_pretrain.py -e riko -sr 40k -f0 1 -bs 1 -te 20 -se 5 -pg pretrained_v2/f0G40k.pth -pd pretrained_v2/f0D40k.pth -l 0 -c 0 -sw 0 -v v2

and then nothing happens.

I'm using an AMD Radeon RX 6800 which RVC doesn't support. I had to change the extract_feature_print.py slightly to get Feature Extraction to work (#512 ).

The output information just gives

训练结束, 您可查看控制台训练日志或实验文件夹下的train.log

which google translates to 'After the training is over, you can check the console training log or train.log under the experiment folder'. I haven't seen any train.log in the experiment folder.

Mugen-CC avatar Jun 17 '23 20:06 Mugen-CC

I have same problem at latest version. On RVC-beta20230516 works fine.

Phtewart avatar Jun 18 '23 09:06 Phtewart

same

Haxhom avatar Dec 29 '23 11:12 Haxhom

This issue was closed because it has been inactive for 15 days since being marked as stale.

github-actions[bot] avatar Apr 28 '24 04:04 github-actions[bot]

Same here, and there is no train.log file or anything. (Is it even possible to train models using CPU mode?)

kalbright3275 avatar Aug 08 '24 21:08 kalbright3275