| | |
|---|
| | | from typing import Union |
|---|
| | | |
|---|
| | | import torch |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.models.e2e_asr_common import ErrorCalculator |
|---|
| | | from funasr.modules.nets_utils import th_accuracy |
|---|
| | |
|---|
| | | frontend: Optional[AbsFrontend], |
|---|
| | | specaug: Optional[AbsSpecAug], |
|---|
| | | normalize: Optional[AbsNormalize], |
|---|
| | | preencoder: Optional[AbsPreEncoder], |
|---|
| | | encoder: AbsEncoder, |
|---|
| | | postencoder: Optional[AbsPostEncoder], |
|---|
| | | decoder: AbsDecoder, |
|---|
| | | ctc: CTC, |
|---|
| | | ctc_weight: float = 0.5, |
|---|
| | |
|---|
| | | loss_weight_model1: float = 0.5, |
|---|
| | | enable_maas_finetune: bool = False, |
|---|
| | | freeze_encoder2: bool = False, |
|---|
| | | preencoder: Optional[AbsPreEncoder] = None, |
|---|
| | | postencoder: Optional[AbsPostEncoder] = None, |
|---|
| | | encoder1_encoder2_joint_training: bool = True, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | assert 0.0 <= ctc_weight <= 1.0, ctc_weight |
|---|
| | | assert 0.0 <= interctc_weight < 1.0, interctc_weight |
|---|
| | | |
|---|
| | |
|---|
| | | self.enable_maas_finetune = enable_maas_finetune |
|---|
| | | self.freeze_encoder2 = freeze_encoder2 |
|---|
| | | self.encoder1_encoder2_joint_training = encoder1_encoder2_joint_training |
|---|
| | | self.length_normalized_loss = length_normalized_loss |
|---|
| | | |
|---|
| | | def forward( |
|---|
| | | self, |
|---|
| | |
|---|
| | | stats["loss2"] = torch.clone(loss2.detach()) |
|---|
| | | stats["loss"] = torch.clone(loss.detach()) |
|---|
| | | # force_gatherable: to-device and to-tensor if scalar for DataParallel |
|---|
| | | if self.length_normalized_loss: |
|---|
| | | batch_size = int((text_lengths + 1).sum()) |
|---|
| | | loss, stats, weight = force_gatherable((loss, stats, batch_size), loss.device) |
|---|
| | | return loss, stats, weight |
|---|
| | | |
|---|
