melodyless

librosa can support time_stretch and pitch_shif, but can't run in GPU. librosa.effects.time_stretch https://librosa.org/doc/main/generated/librosa.effects.time_stretch.html#librosa.effects.time_stretch librosa.effects.pitch_shift https://librosa.org/doc/main/generated/librosa.effects.pitch_shift.html#librosa-effects-pitch-shift and the resample feature also very useful for audio processing, such as Julius, fast PyTorch...

Thanks your impressive work. when I use multi-GPU training, such as python -m multiproc train.py --output_directory=outdir --log_directory=logdir --n_gpus=2 --hparams=distributed_run=True I run into the error， as shown below: Traceback (most recent...

thanks for your impressive work. Is the "24kHz and 10 bit mu-law model" training completed?