A Question on Evaluation

[Mr. Feng]

Hello, I am a Chinese student.
I have downloaded two solo videos（2P83WJXifEs and 3d1b4UH43-E）from 'val.csv' to evaluate the performance of the model. Finally, loss is 0.5479. The effect of each speech separation is very unsatisfactory. Why is that? hope to get your reply.

P.s. I have download the trained model weights for evaluation by:
> ./ scripts / download_trained_model.sh
and I Evaluate the trained model performance by:
> ./ scripts / eval_MUSIC.sh

[Hang Zhao]

You are using two videos of the same instrument I guess.

[Mr. Feng]

Thank you. I changed two different instruments and the effect was improved.

[MaShuo]

@GFENGG I am a Chinese student too. if you have time, could I ask some questions about this project from you ...my email is [e-mail]. Thank you very much....