[channel, time] else [time, channel].
filepath (str or pathlib.Path) – Path to save file. This function also handles pathlib.Path objects, but is annotated
as str for TorchScript compiler compatibility.
tensor (torch.Tensor) – Audio data to save. must be 2D tensor.
tensor (torch.Tensor) – Audio data to save. must be 2D tensor.
sample_rate (int) – sampling rate
channels_first (bool) – If True, the given tensor is interpreted as [channel, time],
otherwise [time, channel].
[channel, time] else [time, channel].
pathlib.Path objects, but is annotated as str
for the consistency with “sox_io” backend, which has a restriction on type annotation
for TorchScript compiler compatiblity.tensor (torch.Tensor) – Audio data to save. must be 2D tensor.
tensor (torch.Tensor) – Audio data to save. must be 2D tensor.
sample_rate (int) – sampling rate
channels_first (bool) – If True, the given tensor is interpreted as [channel, time],
otherwise [time, channel].
All datasets are subclasses of torch.utils.data.Dataset
+
All datasets are subclasses of torch.utils.data.Dataset
i.e, they have __getitem__ and __len__ methods implemented.
-Hence, they can all be passed to a torch.utils.data.DataLoader
+Hence, they can all be passed to a torch.utils.data.DataLoader
which can load multiple samples parallelly using torch.multiprocessing workers.
For example:
yesno_data = torchaudio.datasets.YESNO('.', download=True)
@@ -1016,10 +1045,6 @@ Resources
Get Started
- waveform (torch.Tensor) – audio waveform of dimension of (…, time)
waveform (torch.Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
cutoff_freq (float) – filter cutoff frequency
Q (float, optional) – https://en.wikipedia.org/wiki/Q_factor (Default: 0.707)
waveform (torch.Tensor) – audio waveform of dimension of (…, time)
waveform (torch.Tensor) – audio waveform of dimension of (…, time)
sample_rate (int) – sampling rate of the waveform, e.g. 44100 (Hz)
central_freq (float) – central frequency (in Hz)
Q (float, optional) – https://en.wikipedia.org/wiki/Q_factor (Default: 0.707)
To use this module, the dependency kaldi_io needs to be installed.
-This is a light wrapper around kaldi_io that returns torch.Tensor.
kaldi_io that returns torch.Tensor.
input (torch.Tensor) – 3D Tensor with shape [batch, channel==1, frames]
+input (torch.Tensor) – 3D Tensor with shape [batch, channel==1, frames]
3D Tensor with shape [batch, channel==num_sources, frames]
x (torch.Tensor) – Tensor of dimension (batch_size, num_features, input_length).
+x (torch.Tensor) – Tensor of dimension (batch_size, num_features, input_length).
Predictor tensor of dimension (batch_size, number_of_classes, input_length).
@@ -649,10 +678,6 @@tensor (torch.Tensor) – Input 2D Tensor.
tensor (torch.Tensor) – Input 2D Tensor.
sample_rate (int) – Sample rate
effects (List[List[str]]) – List of effects.
channels_first (bool) – Indicates if the input Tensor’s dimension is @@ -372,7 +401,7 @@
Tuple[torch.Tensor, int]
+Tuple[torch.Tensor, int]
Tuple[torch.Tensor, int]
+Tuple[torch.Tensor, int]
Transforms are common audio transforms. They can be chained together using torch.nn.Sequential
Transforms are common audio transforms. They can be chained together using torch.nn.Sequential