| | |
|---|
| | | from typing import Union |
|---|
| | | |
|---|
| | | import torch |
|---|
| | | from typeguard import check_argument_types |
|---|
| | | |
|---|
| | | from funasr.layers.abs_normalize import AbsNormalize |
|---|
| | | from funasr.losses.label_smoothing_loss import ( |
|---|
| | |
|---|
| | | yield |
|---|
| | | |
|---|
| | | |
|---|
| | | class ESPnetASRModel(FunASRModel): |
|---|
| | | class ASRModel(FunASRModel): |
|---|
| | | """CTC-attention hybrid Encoder-Decoder model""" |
|---|
| | | |
|---|
| | | def __init__( |
|---|
| | |
|---|
| | | 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, |
|---|
| | |
|---|
| | | sym_space: str = "<space>", |
|---|
| | | sym_blank: str = "<blank>", |
|---|
| | | extract_feats_in_collect_stats: bool = True, |
|---|
| | | preencoder: Optional[AbsPreEncoder] = None, |
|---|
| | | postencoder: Optional[AbsPostEncoder] = None, |
|---|
| | | ): |
|---|
| | | assert check_argument_types() |
|---|
| | | assert 0.0 <= ctc_weight <= 1.0, ctc_weight |
|---|
| | | assert 0.0 <= interctc_weight < 1.0, interctc_weight |
|---|
| | | |
|---|
