Dabi Ahn
Dabi Ahn
@dankorg Actually I didn't try to target speech denoising task with the same model. But I think it would work with the speech denoising task as well. I expect the...
@ShengleiH What I mentioned in README is the summary of the paper written by Po-Sen. In my work, I didn't apply the circular shifting technique whereas I used cropping waveforms...
@lemonsee hmm.. I'm not sure but this could be the answer.. https://stackoverflow.com/questions/38836269/does-tensorflow-view-all-cpus-of-one-machine-as-one-device
@dankorg It will work if you set right dataset path in config.py. Right before I uploaded MIR-1K dataset which is public to use. You can train the model by running...
@ShengleiH please check the version of librosa and let me know. I used 0.5.1.
@dankorg please use eval.py to test. set NUM_EVAL (the number of test you want) and DATA_PATH in config.py. you can use either mono or stereo.
@dankorg the result will be shown in Tensorboard audio tab. You can play the result wav directly in there :)
@dankorg you have two options. 1. I just updated the code and now the result is written to result_path. set WRITE_RESULT to True to write result wavs. 2. download the...
@xuerq My models are still in training so I think I could get samples a few days later.
@ChristopherLu @colinsongf I proprocessed voxceleb dataset to be sample rate 16,000 that is my config in default.yaml