Commits on Nov 28, 2020

1. fix: dataset-folder-in-archive flag is empty …

   In line [151-160](https://github.com/pytorch/audio/blob/master/examples/pipeline_wav2letter/main.py#L151) and Line [437](https://github.com/pytorch/audio/blob/fb3ef9ba427acd7db3084f988ab55169fab14854/examples/pipeline_wav2letter/main.py#L437) of main.py, the default value of `dataset-root` and `dataset-folder-in-archive` will be None, which prevents `main.py` from knowing where the dataset is actually in the computer and loading it.
   
   Moreover, `n-hidden-channels 2000` has not been defined in `main.py`, so it needs to be removed.
   
   Erro log:
   
   ```bash
   python main.py \
       --reduce-lr-valid \
       --dataset-train train-clean-100 train-clean-360 train-other-500 \
       --dataset-valid dev-clean \
       --batch-size 128 \
       --learning-rate .6 \
       --momentum .8 \
       --weight-decay .00001 \
       --clip-grad 0. \
       --gamma .99 \
       --hop-length 160 \
       --win-length 400 \
       --n-bins 13 \
       --normalize \
       --optimizer adadelta \
       --scheduler reduceonplateau \                                         
       --epochs 30
   
   /home/hoangtnm/anaconda3/envs/dl/lib/python3.7/site-packages/torchaudio/backend/utils.py:54: UserWarning: "sox" backend is being deprecated. The default backend will be changed to "sox_io" backend in 0.8.0 and "sox" backend will be removed in 0.9.0. Please migrate to "sox_io" backend. Please refer to pytorch#903 for the detail.
     '"sox" backend is being deprecated. '
   INFO:root:Namespace(batch_size=128, checkpoint='', clip_grad=0.0, dataset_folder_in_archive=None, dataset_root=None, dataset_train=['train-clean-100', 'train-clean-360', 'train-other-500'], dataset_valid=['dev-clean'], decoder='greedy', distributed=False, epochs=30, eps=1e-08, freq_mask=0, gamma=0.99, hop_length=160, jit=False, learning_rate=0.6, momentum=0.8, n_bins=13, normalize=True, optimizer='adadelta', progress_bar=False, reduce_lr_valid=True, rho=0.95, scheduler='reduceonplateau', seed=0, start_epoch=0, time_mask=0, type='mfcc', weight_decay=1e-05, win_length=400, workers=0, world_size=8)
   INFO:root:Start time: 2020-11-28 21:18:22.337478
   /home/hoangtnm/anaconda3/envs/dl/lib/python3.7/site-packages/torchaudio/backend/utils.py:64: UserWarning: The interface of "soundfile" backend is planned to change in 0.8.0 to match that of "sox_io" backend and the current interface will be removed in 0.9.0. To use the new interface, do `torchaudio.USE_SOUNDFILE_LEGACY_INTERFACE = False` before setting the backend to "soundfile". Please refer to pytorch#903 for the detail.
     'The interface of "soundfile" backend is planned to change in 0.8.0 to '
   Traceback (most recent call last):
     File "main.py", line 670, in <module>
       spawn_main(main, args)
     File "main.py", line 663, in spawn_main
       main(0, args)
     File "main.py", line 454, in main
       root=args.dataset_root,
     File "/media/aiteam/DATA/workspace/hoangtnm/audio/examples/pipeline_wav2letter/src/datasets.py", line 65, in split_process_vlsp2020asr
       return tuple(create(dataset) for dataset in datasets)
     File "/media/aiteam/DATA/workspace/hoangtnm/audio/examples/pipeline_wav2letter/src/datasets.py", line 65, in <genexpr>
       return tuple(create(dataset) for dataset in datasets)
     File "/media/aiteam/DATA/workspace/hoangtnm/audio/examples/pipeline_wav2letter/src/datasets.py", line 57, in create
       for tag, transform in zip(tags, transform_list)
     File "/media/aiteam/DATA/workspace/hoangtnm/audio/examples/pipeline_wav2letter/src/datasets.py", line 57, in <listcomp>
       for tag, transform in zip(tags, transform_list)
     File "/media/aiteam/DATA/workspace/hoangtnm/audio/examples/pipeline_wav2letter/src/datasets.py", line 15, in __init__
       self._path = os.path.join(root, url)
     File "/home/hoangtnm/anaconda3/envs/dl/lib/python3.7/posixpath.py", line 80, in join
       a = os.fspath(a)
   TypeError: expected str, bytes or os.PathLike object, not NoneType
   ```

   

   hoangtnm committed Nov 28, 2020
   Configuration menu

   • View commit details
   • Copy full SHA for c6b5e74
   • Browse repository at this point

   Copy the full SHA

   c6b5e74 View commit details

   Browse the repository at this point in the history