search

ZFTurbo / Music-Source-Separation-Training

Repository for training models for music source separation.
246 stars 31 forks source link

extract_instrumental #28

Open ghost opened 1 month ago

ghost commented 1 month ago

python inference.py \
--model_type mdx23c \ --config_path configs/config_mdx23c_musdb18.yaml \ --start_check_point results/last_mdx23c.ckpt \ --input_folder input/wavs/ \ --store_dir separation_results/

--extract_instrumental ??

How should I write the extract_instrumental field?

ZFTurbo commented 1 month ago

You only need to add -extract_instrumental. That's all

wdos3 commented 1 month ago

Even with adding that flag, the program still generates both the vocal and the other (instrumental) version, and still takes double the time, is there a fix for it?

ZFTurbo commented 1 month ago

Even with adding that flag, the program still generates both the vocal and the other (instrumental) version, and still takes double the time, is there a fix for it?

I think it's not possible this flag will take double time. Can you add more details about your problem?