Closed XCYu-0903 closed 6 months ago
Due to the use of self-attention in our model to capture global information, the length of segments has a significant impact on model performance.
Additionally, validating only once per epoch may be too infrequent. You can perform more validations to find relatively good checkpoints, but this should have a minor impact.
Dear yxlu-0102: Thank you for your prompt reply! Following your suggestions, I will restore segment_size to 32000, modify batch=2 (1 batch per GPU) and retrain the model later.
How many steps did you train? I trained on 2x3090 with default config for 160k steps but the best pesq checkpoint stuck at 3.27 since 55k steps. Looking forward to your reply.
I trained the model for about 500k steps, but the value of PESQ will not vary significantly between 300k and 500k steps. You can observe the value of PESQ through tensorboard.
Hello! Your paper and codes are very enlightening to me and I tried to train the model from scratch on VCTK-DEMAND dataset to reproduce the results, but I found that the metrics are rather lower than those provided in the article. PESQ, CSIG, CBAK and COVL are merely about 3.39, 4.67, 3.84 and 4.14, respectively. I modified the following parts of the codes: