tasnet

class recipes.cad2.task2.ConvTasNet.local.tasnet.ChannelwiseLayerNorm(channel_size)[source]

Bases: Module

Channel-wise Layer Normalization (cLN)

forward(y)[source]

Parameters:: y – [M, N, K], M is batch size, N is channel size, K is length
Returns:: [M, N, K]
Return type:: cLN_y

reset_parameters()[source]

class recipes.cad2.task2.ConvTasNet.local.tasnet.Chomp1d(chomp_size)[source]

Bases: Module

To ensure the output length is the same as the input.

forward(x)[source]

Parameters:: x – [M, H, Kpad]
Returns:: [M, H, K]

class recipes.cad2.task2.ConvTasNet.local.tasnet.ConvTasNetStereo(*args: Any, **kwargs: Any)[source]

Bases: Module, PyTorchModelHubMixin

forward(mixture)[source]

Parameters:: mixture – [M, T], M is batch size, T is #samples
Returns:: [M, C, T]
Return type:: est_source

get_model_args()[source]: Arguments needed to re-instantiate the model.

get_state_dict()[source]: In case the state dict needs to be modified before sharing the model.

serialize()[source]

Serialize model and output dictionary.

Returns:: dict, serialized model with keys model_args and state_dict.

valid_length(length)[source]

class recipes.cad2.task2.ConvTasNet.local.tasnet.Decoder(N, L, audio_channels)[source]

Bases: Module

forward(mixture_w, est_mask)[source]

Parameters:

mixture_w – [M, N, K]
est_mask – [M, C, N, K]

Returns:

[M, C, T]

Return type:

est_source

class recipes.cad2.task2.ConvTasNet.local.tasnet.DepthwiseSeparableConv(in_channels, out_channels, kernel_size, stride, padding, dilation, norm_type='gLN', causal=False)[source]

Bases: Module

forward(x)[source]

Parameters:: x – [M, H, K]
Returns:: [M, B, K]
Return type:: result

class recipes.cad2.task2.ConvTasNet.local.tasnet.Encoder(L, N, audio_channels)[source]

Bases: Module

Estimation of the nonnegative mixture weight by a 1-D conv layer.

forward(mixture)[source]

Parameters:: mixture – [M, T], M is batch size, T is #samples
Returns:: [M, N, K], where K = (T-L)/(L/2)+1 = 2T/L-1
Return type:: mixture_w

class recipes.cad2.task2.ConvTasNet.local.tasnet.GlobalLayerNorm(channel_size)[source]

Bases: Module

Global Layer Normalization (gLN)

forward(y)[source]

Parameters:: y – [M, N, K], M is batch size, N is channel size, K is length
Returns:: [M, N, K]
Return type:: gLN_y

reset_parameters()[source]

class recipes.cad2.task2.ConvTasNet.local.tasnet.TemporalBlock(in_channels, out_channels, kernel_size, stride, padding, dilation, norm_type='gLN', causal=False)[source]

Bases: Module

forward(x)[source]

Parameters:: x – [M, B, K]
Returns:: [M, B, K]

class recipes.cad2.task2.ConvTasNet.local.tasnet.TemporalConvNet(N, B, H, P, X, R, C, norm_type='gLN', causal=False, mask_nonlinear='relu')[source]

Bases: Module

forward(mixture_w)[source]

Keep this API same with TasNet :param mixture_w: [M, N, K], M is batch size

Returns:: [M, C, N, K]
Return type:: est_mask

recipes.cad2.task2.ConvTasNet.local.tasnet.chose_norm(norm_type, channel_size)[source]: The input of normlization will be (M, C, K), where M is batch size, C is channel size and K is sequence length.

recipes.cad2.task2.ConvTasNet.local.tasnet.overlap_and_add(signal, frame_step)[source]