search

ZFTurbo / Music-Source-Separation-Training

Repository for training models for music source separation.
MIT License
485 stars 67 forks source link

MelBand RoFormer Vocal pre-trained model: Missing key(s) in state_dict and size mismatch for mask_estimators #59

Closed hunterhogan closed 3 months ago

hunterhogan commented 3 months ago

Errors when running inference using the pre-trained MelBand RoFormer Vocal model and the associated Config file.

RuntimeError: Error(s) in loading state_dict for MelBandRoformer:
    Missing key(s) in state_dict: "mask_estimators.0.to_freqs.0.0.4.weight", "mask_estimators.0.to_freqs.0.0.4.bias", ... 
    size mismatch for mask_estimators.0.to_freqs.0.0.2.weight: copying a param with shape torch.Size([56, 768]) from checkpoint, the shape in current model is torch.Size([768, 768]).
    size mismatch for mask_estimators.0.to_freqs.0.0.2.bias: copying a param with shape torch.Size([56]) from checkpoint, the shape in current model is torch.Size([768]). ...

There are some differences between the file linked in readme and the file in the main branch, but the errors happen with either file.

I don't have much useful information to add, but I did make a Colab notebook to eliminate variables. You can use it, too. It takes about four minutes to install and produce the error. https://colab.research.google.com/drive/1XTTWrs-FJKotFYtH8goTpaT3lIOTKUv1?usp=sharing

ZFTurbo commented 3 months ago

I didn't understand which model and whcih config file you mention.

hunterhogan commented 3 months ago

Weights https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.0/model_vocals_mel_band_roformer_sdr_8.42.ckpt

Readme config https://github.com/ZFTurbo/Music-Source-Separation-Training/releases/download/v1.0.0/config_vocals_mel_band_roformer.yaml

And I made cells to try the config files in the main branch: configs/config_vocals_mel_band_roformer.yaml configs/config_musdb18_mel_band_roformer.yaml

ZFTurbo commented 3 months ago

I think it's better just remove this model from list because it's old and weak.

hunterhogan commented 3 months ago

I won't tell your grandparents you said that.

(peace) سلام, 和谐 (group harmony), health, and happiness,

Hunter

Sent from Proton Mail Android

-------- Original Message -------- On 8/14/24 8:59 AM, Roman Solovyev wrote:

I think it's better just remove this model from list because it's old and weak.

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

hunterhogan commented 3 months ago

Euthanized.