Jasper

Jasper

class kospeech.models.jasper.model.Jasper(num_classes: int, version: str = '10x5', device: torch.device = 'cuda')

Jasper: An End-to-End Convolutional Neural Acoustic Model Jasper (Just Another Speech Recognizer), an ASR model comprised of 54 layers proposed by NVIDIA. Jasper achieved sub 3 percent word error rate (WER) on the LibriSpeech dataset. More details: https://arxiv.org/pdf/1904.03288.pdf

Parameters

• num_classes (int) – number of classification

• version (str) – version of jasper. Marked as BxR: B - number of blocks, R - number of sub-blocks

• device (torch.device) – device - ‘cuda’ or ‘cpu’

Inputs: inputs, input_lengths, residual

• inputs: tensor contains input sequence vector

• input_lengths: tensor contains sequence lengths

Returns: output, output_lengths

• output: tensor contains output sequence vector

• output: tensor contains output sequence lengths

forward(inputs: torch.Tensor, input_lengths: torch.Tensor) → Tuple[torch.Tensor, torch.Tensor]

Forward propagate a inputs for ctc training.

Parameters

• inputs (torch.FloatTensor) – A input sequence passed to encoder. Typically for inputs this will be a padded FloatTensor of size (batch, seq_length, dimension).

• input_lengths (torch.LongTensor) – The length of input tensor. (batch)

Returns

• predicted_log_prob (torch.FloatTensor)s: Log probability of model predictions.

• output_lengths (torch.LongTensor): The length of output tensor (batch)

Return type

(Tensor, Tensor)

Sublayers

class kospeech.models.jasper.sublayers.JasperBlock(num_sub_blocks: int, in_channels: int, out_channels: int, kernel_size: int, stride: int = 1, dilation: int = 1, bias: bool = True, dropout_p: float = 0.2, activation: str = 'relu')

Jasper Block: The Jasper Block consists of R Jasper sub-block.

Parameters

• num_sub_blocks (int) – number of sub block

• in_channels (int) – number of channels in the input feature

• out_channels (int) – number of channels produced by the convolution

• kernel_size (int) – size of the convolving kernel

• stride (int) – stride of the convolution. (default: 1)

• dilation (int) – spacing between kernel elements. (default: 1)

• bias (bool) – if True, adds a learnable bias to the output. (default: True)

• dropout_p (float) – probability of dropout

• activation (str) – activation function

Inputs: inputs, input_lengths, residual

• inputs: tensor contains input sequence vector

• input_lengths: tensor contains sequence lengths

• residual: tensor contains residual vector

Returns: output, output_lengths

• output: tensor contains output sequence vector

• output: tensor contains output sequence lengths

class kospeech.models.jasper.sublayers.JasperSubBlock(in_channels: int, out_channels: int, kernel_size: int, stride: int = 1, dilation: int = 1, padding: int = 0, bias: bool = False, dropout_p: float = 0.2, activation: str = 'relu')

Jasper sub-block applies the following operations: a 1D-convolution, batch norm, ReLU, and dropout.

Parameters

• in_channels (int) – number of channels in the input feature

• out_channels (int) – number of channels produced by the convolution

• kernel_size (int) – size of the convolving kernel

• stride (int) – stride of the convolution. (default: 1)

• dilation (int) – spacing between kernel elements. (default: 1)

• padding (int) – zero-padding added to both sides of the input. (default: 0)

• bias (bool) – if True, adds a learnable bias to the output. (default: False)

• dropout_p (float) – probability of dropout

• activation (str) – activation function

Inputs: inputs, input_lengths, residual

• inputs: tensor contains input sequence vector

• input_lengths: tensor contains sequence lengths

• residual: tensor contains residual vector

Returns: output, output_lengths

• output: tensor contains output sequence vector

• output: tensor contains output sequence lengths