r"""Calculate SDR between reference and estimation. Args: ref (np.ndarray), reference signal est (np.ndarray), estimated signal

Initialize a Linear or Convolutional layer.

Returns the tokenized representation of given input string(s) Parameters ---------- texts : Union[str, List[str]] An input s

r"""Calculate SDR between reference and estimation. Args: ref (np.ndarray), reference signal est (np.ndarray), estimated signal

Initialize a Batchnorm layer.

Initialize a Linear or Convolutional layer.

Args: x: (batch_size , ...) mixup_lambda: (batch_size,) Returns: out: (batch_size, ...)

Interpolate data in time domain. This is used to compensate the resolution reduction in downsampling of a CNN. Args: x: (batch_size, ti

r"""Parse yaml file. Args: config_yaml (str): config yaml path Returns: yaml_dict (Dict): parsed yaml file

Initialize a Batchnorm layer.

r"""Fills the input Tensor with values drawn from a truncated normal distribution. The values are effectively drawn from the normal distributi

Converts all `BatchNorm2d` and `SyncBatchNorm` layers of provided module into `FrozenBatchNorm2d`. If `module` is itself an instance of eithe

Calculate and add audio features to sample. Sample: a dict containing all the data of current sample. audio_data: a tensor of shape (T) c

Returns list of utf-8 byte and a corresponding list of unicode strings. The reversible bpe codes work on unicode strings. This means you

Calculate performance for Clotho+AudioCaps for model selection.

Get the audio embedding from the model Parameters ---------- data: a list of dict the audio input dict list from

Return set of symbol pairs in a word. Word is represented as tuple of symbols (symbols being variable-length strings).

Get tar path from dataset name and type

Get the text embedding from the model Parameters ---------- data: torch.Tensor a tensor of text embedding

enumerate available model architectures based on config files

r"""Load trained universal source separation model. Args: configs (Dict) checkpoint_path (str): path of the checkpoint to load

Args: x: (B, H, W, C) window_size (int): window size Returns: windows: (num_windows*B, window_size, window_size, C)

r"""Get evaluation audio names.