Evaluation seems ton only run on sequences with length < cv_max_len

[lienz]

Hi, Thanks for providing your implementation of Conv-Tasnet. I trained a model and when I evaluated it on the test set (using run.sh) I was surprised to only see 2618 sequences evaluated (while the test set size is 3000). It seems that the AudioDataset created in evaluate.py uses the default cv_maxlen parameter (8 seconds), such that only test sequences shorter than 8 seconds are evaluated (2618 sequences). This would mean that the test SDR is not representative of how well the model performs on longer utterances. I attached the line where the AudioDataset is created. Best regards, Neil https://github.com/kaituoxu/Conv-TasNet/blob/73d42bf3b222d5df1f9538f121280038b0c2da53/src/evaluate.py#L48