DeepSpeech2

DeepSpeech2 Model

class openspeech.models.deepspeech2.model.DeepSpeech2Model(configs: omegaconf.dictconfig.DictConfig, tokenizer: openspeech.tokenizers.tokenizer.Tokenizer)[source]

Deep Speech2 model with configurable encoders and decoders. Paper: https://arxiv.org/abs/1512.02595

Parameters
  • configs (DictConfig) – configuration set.

  • tokenizer (Tokenizer) – 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)

forward(inputs: torch.Tensor, input_lengths: torch.Tensor) → Dict[str, torch.Tensor][source]

Forward propagate a inputs and targets pair for inference.

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)

test_step(batch: tuple, batch_idx: int)collections.OrderedDict[source]

Forward propagate a inputs and targets pair for test.

Inputs:

batch (tuple): A train batch contains inputs, targets, input_lengths, target_lengths batch_idx (int): The index of batch

Returns

loss for training

Return type

loss (torch.Tensor)

training_step(batch: tuple, batch_idx: int)collections.OrderedDict[source]

Forward propagate a inputs and targets pair for training.

Inputs:

batch (tuple): A train batch contains inputs, targets, input_lengths, target_lengths batch_idx (int): The index of batch

Returns

loss for training

Return type

loss (torch.Tensor)

validation_step(batch: tuple, batch_idx: int)collections.OrderedDict[source]

Forward propagate a inputs and targets pair for validation.

Inputs:

batch (tuple): A train batch contains inputs, targets, input_lengths, target_lengths batch_idx (int): The index of batch

Returns

loss for training

Return type

loss (torch.Tensor)

DeepSpeech2 Configuration

class openspeech.models.deepspeech2.configurations.DeepSpeech2Configs(model_name: str = 'deepspeech2', rnn_type: str = 'gru', num_rnn_layers: int = 5, rnn_hidden_dim: int = 1024, dropout_p: float = 0.3, bidirectional: bool = True, activation: str = 'hardtanh', optimizer: str = 'adam')[source]

This is the configuration class to store the configuration of a DeepSpeech2.

It is used to initiated an DeepSpeech2 model.

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

Parameters
  • model_name (str) – Model name (default: deepspeech2)

  • num_rnn_layers (int) – The number of rnn layers. (default: 5)

  • rnn_hidden_dim (int) – The hidden state dimension of rnn. (default: 1024)

  • dropout_p (float) – The dropout probability of model. (default: 0.3)

  • bidirectional (bool) – If True, becomes a bidirectional encoders (default: True)

  • rnn_type (str) – Type of rnn cell (rnn, lstm, gru) (default: gru)

  • activation (str) – Type of activation function (default: str)

  • optimizer (str) – Optimizer for training. (default: adam)