def _setup_metrics(self):
self._mse = MeanSquaredError()
self._mae = MeanAbsoluteError()
class EncDecRegressionModel(_EncDecBaseModel):
"""Encoder decoder class for speech regression models.
Model class creates training, validation methods for setting up data
performing model forward pass.
"""
@classmethod
def list_available_models(cls) -> List[PretrainedModelInfo]:
"""
This method returns a list of pre-trained model which can be instantiated directly from NVIDIA's NGC cloud.
Returns:
List of available pre-trained models.
"""
result = []
return result
def __init__(self, cfg: DictConfig, trainer: Trainer = None):
if not cfg.get('is_regression_task', False):
raise ValueError(
f"EndDecRegressionModel requires the flag is_regression_task to be set as true"
)
super().__init__(cfg=cfg, trainer=trainer)
def _setup_preprocessor(self):
return EncDecRegressionModel.from_config_dict(self._cfg.preprocessor)
def _setup_encoder(self):
return EncDecRegressionModel.from_config_dict(self._cfg.encoder)
def _setup_decoder(self):
return EncDecRegressionModel.from_config_dict(self._cfg.decoder)
def _setup_loss(self):
return MSELoss()
def _setup_metrics(self):
self._mse = MeanSquaredError()
self._mae = MeanAbsoluteError()
@property
def output_types(self) -> Optional[Dict[str, NeuralType]]:
return {"preds": NeuralType(tuple('B'), RegressionValuesType())}
@typecheck()
def forward(self, input_signal, input_signal_length):
logits = super().forward(input_signal=input_signal,
input_signal_length=input_signal_length)
return logits.view(-1)
# PTL-specific methods
def training_step(self, batch, batch_idx):
self.training_step_end()
audio_signal, audio_signal_len, targets, targets_len = batch
logits = self.forward(input_signal=audio_signal,
input_signal_length=audio_signal_len)
loss = self.loss(preds=logits, labels=targets)
train_mse = self._mse(preds=logits, target=targets)
train_mae = self._mae(preds=logits, target=targets)
tensorboard_logs = {
'train_loss': loss,
'train_mse': train_mse,
'train_mae': train_mae,
'learning_rate': self._optimizer.param_groups[0]['lr'],
}
self.log_dict(tensorboard_logs)
return {'loss': loss}
def validation_step(self, batch, batch_idx, dataloader_idx: int = 0):
audio_signal, audio_signal_len, targets, targets_len = batch
logits = self.forward(input_signal=audio_signal,
input_signal_length=audio_signal_len)
loss_value = self.loss(preds=logits, labels=targets)
val_mse = self._mse(preds=logits, target=targets)
val_mae = self._mae(preds=logits, target=targets)
return {'val_loss': loss_value, 'val_mse': val_mse, 'val_mae': val_mae}
def test_step(self, batch, batch_idx, dataloader_idx: int = 0):
logs = self.validation_step(batch, batch_idx, dataloader_idx)
return {
'test_loss': logs['val_loss'],
'test_mse': logs['test_mse'],
'test_mae': logs['val_mae']
}
def multi_validation_epoch_end(self, outputs, dataloader_idx: int = 0):
val_loss_mean = torch.stack([x['val_loss'] for x in outputs]).mean()
val_mse = self._mse.compute()
self._mse.reset()
val_mae = self._mae.compute()
self._mae.reset()
tensorboard_logs = {
'val_loss': val_loss_mean,
'val_mse': val_mse,
'val_mae': val_mae
}
return {
'val_loss': val_loss_mean,
'val_mse': val_mse,
'val_mae': val_mae,
'log': tensorboard_logs
}
def multi_test_epoch_end(self, outputs, dataloader_idx: int = 0):
test_loss_mean = torch.stack([x['test_loss'] for x in outputs]).mean()
test_mse = self._mse.compute()
self._mse.reset()
test_mae = self._mae.compute()
self._mae.reset()
tensorboard_logs = {
'test_loss': test_loss_mean,
'test_mse': test_mse,
'test_mae': test_mae
}
return {
'test_loss': test_loss_mean,
'test_mse': test_mse,
'test_mae': test_mae,
'log': tensorboard_logs
}
@torch.no_grad()
def transcribe(self,
paths2audio_files: List[str],
batch_size: int = 4) -> List[float]:
"""
Generate class labels for provided audio files. Use this method for debugging and prototyping.
Args:
paths2audio_files: (a list) of paths to audio files. \
Recommended length per file is approximately 1 second.
batch_size: (int) batch size to use during inference. \
Bigger will result in better throughput performance but would use more memory.
Returns:
A list of predictions in the same order as paths2audio_files
"""
predictions = super().transcribe(paths2audio_files,
batch_size,
logprobs=True)
return [float(pred) for pred in predictions]
def _update_decoder_config(self, labels, cfg):
OmegaConf.set_struct(cfg, False)
if 'params' in cfg:
cfg.params.num_classes = 1
else:
cfg.num_classes = 1
OmegaConf.set_struct(cfg, True)