Open RevolGMPHL opened 5 months ago
Do you mean sound quality or speed? If sound quality, yes I was expecting better too.
Thanks @lonzi for the answer! Will try out these tips tomorrow.
thanks for the answer~ Although I tried several parameters, I still feel the performance is not as good as the original model.
Can you @lonzi kindly provide us your sampling parameters or add a note in the readme with recommended paramteres?
Thank you so much!
For Music: span_arrangement: 'stride1' use_sampling: true top-p: 0.9 temperature: 3.0 max_cfg_coef: 10.0 min_cfg_coef: 1.0 decoding_iterations (for 10 secs): [20, 10, 10, 10] decoding_iterations (for 30 secs): [60, 10, 10, 10]
See our paper for the ablation studies.
For Sound [audio-magnet models]: span_arrangement: 'stride1' use_sampling: true top-p: 0.8 temperature: 3.5 max_cfg_coef: 20.0 min_cfg_coef: 1.0 decoding_iterations: [20, 10, 10, 10]
*these are the parameters from the paper ablation studies, not necessarily tuned for the open-source models
Why is the performance so poor? Is there a bug, or is the model itself just this poor in performance?