| | |
|---|
| | | from funasr.modules.e2e_asr_common import ErrorCalculator |
|---|
| | | from funasr.modules.nets_utils import th_accuracy |
|---|
| | | from funasr.torch_utils.device_funcs import force_gatherable |
|---|
| | | from funasr.train.abs_espnet_model import AbsESPnetModel |
|---|
| | | from funasr.models.base_model import FunASRModel |
|---|
| | | |
|---|
| | | if LooseVersion(torch.__version__) >= LooseVersion("1.6.0"): |
|---|
| | | from torch.cuda.amp import autocast |
|---|
| | |
|---|
| | | yield |
|---|
| | | |
|---|
| | | |
|---|
| | | class ESPnetSVModel(AbsESPnetModel): |
|---|
| | | class ESPnetSVModel(FunASRModel): |
|---|
| | | """CTC-attention hybrid Encoder-Decoder model""" |
|---|
| | | |
|---|
| | | def __init__( |
|---|
| | |
|---|
| | | text_lengths: torch.Tensor, |
|---|
| | | ) -> Tuple[torch.Tensor, Dict[str, torch.Tensor], torch.Tensor]: |
|---|
| | | """Frontend + Encoder + Decoder + Calc loss |
|---|
| | | |
|---|
| | | Args: |
|---|
| | | speech: (Batch, Length, ...) |
|---|
| | | speech_lengths: (Batch, ) |
|---|
| | |
|---|
| | | self, speech: torch.Tensor, speech_lengths: torch.Tensor |
|---|
| | | ) -> Tuple[torch.Tensor, torch.Tensor]: |
|---|
| | | """Frontend + Encoder. Note that this method is used by asr_inference.py |
|---|
| | | |
|---|
| | | Args: |
|---|
| | | speech: (Batch, Length, ...) |
|---|
| | | speech_lengths: (Batch, ) |
|---|
| | |
|---|
| | | else: |
|---|
| | | # No frontend and no feature extract |
|---|
| | | feats, feats_lengths = speech, speech_lengths |
|---|
| | | return feats, feats_lengths |
|---|
| | | return feats, feats_lengths |
|---|
