Openspeech Language Model¶

class openspeech.models.openspeech_language_model.OpenspeechLanguageModel(configs: omegaconf.dictconfig.DictConfig, tokenizer: openspeech.tokenizers.tokenizer.Tokenizer)[source]¶

Base class for OpenSpeech’s language models.

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 loss, logits, targets, predictions.
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 loss, logits, targets, predictions.
Return type: outputs (dict)

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

Forward propagate a inputs and targets pair for test.

Inputs:: train_batch (tuple): A train batch contains inputs batch_idx (int): The index of batch

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

Forward propagate a inputs and targets pair for training.

Inputs:: train_batch (tuple): A train batch contains inputs batch_idx (int): The index of batch

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

Forward propagate a inputs and targets pair for validation.

Inputs:: train_batch (tuple): A train batch contains inputs batch_idx (int): The index of batch