How to apply augmentation to audio data

[talhaanwarch]

I am checking how to apply augmentation
I tried this

datamodule = AudioClassificationData.from_files(
    train_files=list(train_df.path),
    train_targets=list(train_df.target),
    sampling_rate=16000,
    transform_kwargs=dict(spectrogram_size=(128, 128),time_mask_param=10, freq_mask_param=10),
    batch_size=8,
)

I even try this

from flash.audio.classification.input_transform import AudioClassificationInputTransform
transform=AudioClassificationInputTransform(freq_mask_param=10,spectrogram_size=(128,128),time_mask_param=10)

but when i do
test=next(iter(datamodule.train_dataloader()))
It throw following error

TypeError                                 Traceback (most recent call last)
[<ipython-input-25-3f937f543ae5>](https://localhost:8080/#) in <module>()
----> 1 test=next(iter(datamodule.train_dataloader()))

15 frames
[/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py](https://localhost:8080/#) in __next__(self)
    528             if self._sampler_iter is None:
    529                 self._reset()
--> 530             data = self._next_data()
    531             self._num_yielded += 1
    532             if self._dataset_kind == _DatasetKind.Iterable and \

[/usr/local/lib/python3.7/dist-packages/torch/utils/data/dataloader.py](https://localhost:8080/#) in _next_data(self)
    568     def _next_data(self):
    569         index = self._next_index()  # may raise StopIteration
--> 570         data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
    571         if self._pin_memory:
    572             data = _utils.pin_memory.pin_memory(data)

[/usr/local/lib/python3.7/dist-packages/torch/utils/data/_utils/fetch.py](https://localhost:8080/#) in fetch(self, possibly_batched_index)
     50         else:
     51             data = self.dataset[possibly_batched_index]
---> 52         return self.collate_fn(data)

[/usr/local/lib/python3.7/dist-packages/flash/core/data/io/input_transform.py](https://localhost:8080/#) in __call__(self, samples)
    800                 list_samples = samples
    801 
--> 802             transformed_samples = [self.per_sample_transform(sample, self.stage) for sample in list_samples]
    803 
    804             for sample in transformed_samples:

[/usr/local/lib/python3.7/dist-packages/flash/core/data/io/input_transform.py](https://localhost:8080/#) in <listcomp>(.0)
    800                 list_samples = samples
    801 
--> 802             transformed_samples = [self.per_sample_transform(sample, self.stage) for sample in list_samples]
    803 
    804             for sample in transformed_samples:

[/usr/local/lib/python3.7/dist-packages/flash/core/data/io/input_transform.py](https://localhost:8080/#) in _per_sample_transform(self, sample, stage)
    618         if isinstance(sample, list):
    619             return [fn(s) for s in sample]
--> 620         return fn(sample)
    621 
    622     def _per_batch_transform(self, batch: Any, stage: RunningStage) -> Any:

[/usr/local/lib/python3.7/dist-packages/torchvision/transforms/transforms.py](https://localhost:8080/#) in __call__(self, img)
     93     def __call__(self, img):
     94         for t in self.transforms:
---> 95             img = t(img)
     96         return img
     97 

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1108         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1109                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110             return forward_call(*input, **kwargs)
   1111         # Do not call functions when jit is used
   1112         full_backward_hooks, non_full_backward_hooks = [], []

[/usr/local/lib/python3.7/dist-packages/flash/core/data/transforms.py](https://localhost:8080/#) in forward(self, x)
     45 
     46         if len(inputs) == 1:
---> 47             result[keys[0]] = super().forward(inputs[0])
     48         elif len(inputs) > 1:
     49             try:

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/container.py](https://localhost:8080/#) in forward(self, input)
    139     def forward(self, input):
    140         for module in self:
--> 141             input = module(input)
    142         return input
    143 

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1108         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1109                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110             return forward_call(*input, **kwargs)
   1111         # Do not call functions when jit is used
   1112         full_backward_hooks, non_full_backward_hooks = [], []

[/usr/local/lib/python3.7/dist-packages/flash/core/data/utils.py](https://localhost:8080/#) in forward(self, *args, **kwargs)
    138 
    139     def forward(self, *args, **kwargs) -> Any:
--> 140         return self.func(*args, **kwargs)
    141 
    142     def __str__(self) -> str:

[/usr/local/lib/python3.7/dist-packages/torchvision/transforms/transforms.py](https://localhost:8080/#) in __call__(self, img)
     93     def __call__(self, img):
     94         for t in self.transforms:
---> 95             img = t(img)
     96         return img
     97 

[/usr/local/lib/python3.7/dist-packages/torch/nn/modules/module.py](https://localhost:8080/#) in _call_impl(self, *input, **kwargs)
   1108         if not (self._backward_hooks or self._forward_hooks or self._forward_pre_hooks or _global_backward_hooks
   1109                 or _global_forward_hooks or _global_forward_pre_hooks):
-> 1110             return forward_call(*input, **kwargs)
   1111         # Do not call functions when jit is used
   1112         full_backward_hooks, non_full_backward_hooks = [], []

[/usr/local/lib/python3.7/dist-packages/torchaudio/transforms.py](https://localhost:8080/#) in forward(self, specgram, mask_value)
   1136             return F.mask_along_axis_iid(specgram, self.mask_param, mask_value, self.axis + 1, p=self.p)
   1137         else:
-> 1138             return F.mask_along_axis(specgram, self.mask_param, mask_value, self.axis, p=self.p)
   1139 
   1140 

[/usr/local/lib/python3.7/dist-packages/torchaudio/functional/functional.py](https://localhost:8080/#) in mask_along_axis(specgram, mask_param, mask_value, axis, p)
    797 
    798     # pack batch
--> 799     shape = specgram.size()
    800     specgram = specgram.reshape([-1] + list(shape[-2:]))
    801     value = torch.rand(1) * mask_param

TypeError: 'int' object is not callable