QuartzNet Model

QuartzNet Model

class openspeech.models.quartznet.model.QuartzNet10x5Model(configs: omegaconf.dictconfig.DictConfig, tokenizer: openspeech.tokenizers.tokenizer.Tokenizer)[source]

QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS Paper: https://arxiv.org/abs/1910.10261.pdf

Parameters
  • configs (DictConfig) – configuration set.

  • tokenizer (Tokeizer) – tokenizer is in charge of preparing the inputs for a model.

Inputs:

inputs (torch.FloatTensor): A input sequence passed to encoders. 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

Result of model predictions that contains y_hats, logits, output_lengths

Return type

outputs (dict)

class openspeech.models.quartznet.model.QuartzNet15x5Model(configs: omegaconf.dictconfig.DictConfig, tokenizer: openspeech.tokenizers.tokenizer.Tokenizer)[source]

QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS Paper: https://arxiv.org/abs/1910.10261.pdf

Parameters
  • configs (DictConfig) – configuration set.

  • tokenizer (Tokeizer) – tokenizer is in charge of preparing the inputs for a model.

Inputs:

inputs (torch.FloatTensor): A input sequence passed to encoders. 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

Result of model predictions that contains y_hats, logits, output_lengths

Return type

outputs (dict)

class openspeech.models.quartznet.model.QuartzNet5x5Model(configs: omegaconf.dictconfig.DictConfig, tokenizer: openspeech.tokenizers.tokenizer.Tokenizer)[source]

QUARTZNET: DEEP AUTOMATIC SPEECH RECOGNITION WITH 1D TIME-CHANNEL SEPARABLE CONVOLUTIONS Paper: https://arxiv.org/abs/1910.10261.pdf

Parameters
  • configs (DictConfig) – configuration set.

  • tokenizer (Tokeizer) – tokenizer is in charge of preparing the inputs for a model.

Inputs:

inputs (torch.FloatTensor): A input sequence passed to encoders. 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

Result of model predictions that contains y_hats, logits, output_lengths

Return type

outputs (dict)

QuartzNet Configuration

class openspeech.models.quartznet.configurations.QuartzNet10x5Configs(model_name: str = 'quartznet10x5', num_blocks: int = 10, num_sub_blocks: int = 5, in_channels: str = '(None, 256, 256, 256, 256, 256, 512, 512, 512, 512, 512, 512, 512, 1024)', out_channels: str = '(256, 256, 256, 256, 256, 512, 512, 512, 512, 512, 512, 512, 1024, None)', kernel_size: str = '(33, 33, 33, 39, 39, 51, 51, 63, 63, 75, 75, 87, 1, 1)', dilation: str = '(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2)', dropout_p: str = '(0.2, None, None, None, None, None, None, None, None, None, None, 0.2, 0.2, 0.2)', optimizer: str = 'novograd')[source]

This is the configuration class to store the configuration of a QuartzNet10x5.

It is used to initiated an QuartzNet10x5 model.

Configuration objects inherit from :class: ~openspeech.dataclass.configs.OpenspeechDataclass.

Parameters
  • model_name (str) – Model name (default: quartznet5x5)

  • num_blocks (int) – Number of quartznet blocks (default: 10)

  • num_sub_blocks (int) – Number of quartznet sub blocks (default: 5)

  • in_channels (str) – Output channels of jasper block’s convolution

  • out_channels (str) – Output channels of jasper block’s convolution

  • kernel_size (str) – Kernel size of jasper block’s convolution

  • dilation (str) – Dilation of jasper block’s convolution

  • dropout_p (str) – Dropout probability

  • optimizer (str) – Optimizer for training.

class openspeech.models.quartznet.configurations.QuartzNet15x5Configs(model_name: str = 'quartznet15x5', num_blocks: int = 15, num_sub_blocks: int = 5, in_channels: str = '(None, 256, 256, 256, 256, 256, 256, 256, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 1024)', out_channels: str = '(256, 256, 256, 256, 256, 256, 256, 512, 512, 512, 512, 512, 512, 512, 512, 512, 512, 1024, None)', kernel_size: str = '(33, 33, 33, 33, 39, 39, 39, 51, 51, 51, 63, 63, 63, 75, 75, 75, 87, 1, 1)', dilation: str = '(1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 2)', dropout_p: str = '(0.2, None, None, None, None, None, None, None, None, None, None, None, None, None, None, None, 0.2, 0.2, 0.2)', optimizer: str = 'novograd')[source]

This is the configuration class to store the configuration of a QuartzNet15x5.

It is used to initiated an QuartzNet15x5 model.

Configuration objects inherit from :class: ~openspeech.dataclass.configs.OpenspeechDataclass.

Parameters
  • model_name (str) – Model name (default: quartznet15x5)

  • num_blocks (int) – Number of quartznet blocks (default: 15)

  • num_sub_blocks (int) – Number of quartznet sub blocks (default: 5)

  • in_channels (str) – Output channels of jasper block’s convolution

  • out_channels (str) – Output channels of jasper block’s convolution

  • kernel_size (str) – Kernel size of jasper block’s convolution

  • dilation (str) – Dilation of jasper block’s convolution

  • dropout_p (str) – Dropout probability

  • optimizer (str) – Optimizer for training.

class openspeech.models.quartznet.configurations.QuartzNet5x5Configs(model_name: str = 'quartznet5x5', num_blocks: int = 5, num_sub_blocks: int = 5, in_channels: str = '(None, 256, 256, 256, 512, 512, 512, 512, 1024)', out_channels: str = '(256, 256, 256, 512, 512, 512, 512, 1024, None)', kernel_size: str = '(33, 33, 39, 51, 63, 75, 87, 1, 1)', dilation: str = '(1, 1, 1, 1, 1, 1, 1, 1, 2)', dropout_p: str = '(0.2, None, None, None, None, None, 0.2, 0.2, 0.2)', optimizer: str = 'novograd')[source]

This is the configuration class to store the configuration of a QuartzNet5x5.

It is used to initiated an QuartzNet5x5 model.

Configuration objects inherit from :class: ~openspeech.dataclass.configs.OpenspeechDataclass.

Parameters
  • model_name (str) – Model name (default: quartznet5x5)

  • num_blocks (int) – Number of quartznet blocks (default: 5)

  • num_sub_blocks (int) – Number of quartznet sub blocks (default: 5)

  • in_channels (str) – Output channels of jasper block’s convolution

  • out_channels (str) – Output channels of jasper block’s convolution

  • kernel_size (str) – Kernel size of jasper block’s convolution

  • dilation (str) – Dilation of jasper block’s convolution

  • dropout_p (str) – Dropout probability

  • optimizer (str) – Optimizer for training.