Initialize LLMASR4. Args: specaug: TODO. specaug_conf: Configuration dict for specaug. normalize: TODO. normalize_conf: Configuration dict for normalize. audio_encoder: TODO. audio_en
(
self,
specaug: str = None,
specaug_conf: dict = None,
normalize: str = None,
normalize_conf: dict = None,
audio_encoder: str = None,
audio_encoder_conf: dict = None,
audio_adaptor: str = None,
audio_adaptor_conf: dict = None,
decoder: str = None,
decoder_conf: dict = None,
ctc: str = None,
ctc_conf: dict = None,
ctc_weight: float = 0.5,
llm: str = None,
llm_conf: dict = None,
input_size: int = 80,
vocab_size: int = -1,
ignore_id: int = -1,
blank_id: int = 0,
sos: int = 1,
eos: int = 2,
lsm_weight: float = 0.0,
length_normalized_loss: bool = False,
report_cer: bool = True,
report_wer: bool = True,
sym_space: str = "<space>",
sym_blank: str = "<blank>",
# extract_feats_in_collect_stats: bool = True,
share_embedding: bool = False,
# preencoder: Optional[AbsPreEncoder] = None,
# postencoder: Optional[AbsPostEncoder] = None,
**kwargs,
)
| 978 | """ """ |
| 979 | |
| 980 | def __init__( |
| 981 | self, |
| 982 | specaug: str = None, |
| 983 | specaug_conf: dict = None, |
| 984 | normalize: str = None, |
| 985 | normalize_conf: dict = None, |
| 986 | audio_encoder: str = None, |
| 987 | audio_encoder_conf: dict = None, |
| 988 | audio_adaptor: str = None, |
| 989 | audio_adaptor_conf: dict = None, |
| 990 | decoder: str = None, |
| 991 | decoder_conf: dict = None, |
| 992 | ctc: str = None, |
| 993 | ctc_conf: dict = None, |
| 994 | ctc_weight: float = 0.5, |
| 995 | llm: str = None, |
| 996 | llm_conf: dict = None, |
| 997 | input_size: int = 80, |
| 998 | vocab_size: int = -1, |
| 999 | ignore_id: int = -1, |
| 1000 | blank_id: int = 0, |
| 1001 | sos: int = 1, |
| 1002 | eos: int = 2, |
| 1003 | lsm_weight: float = 0.0, |
| 1004 | length_normalized_loss: bool = False, |
| 1005 | report_cer: bool = True, |
| 1006 | report_wer: bool = True, |
| 1007 | sym_space: str = "<space>", |
| 1008 | sym_blank: str = "<blank>", |
| 1009 | # extract_feats_in_collect_stats: bool = True, |
| 1010 | share_embedding: bool = False, |
| 1011 | # preencoder: Optional[AbsPreEncoder] = None, |
| 1012 | # postencoder: Optional[AbsPostEncoder] = None, |
| 1013 | **kwargs, |
| 1014 | ): |
| 1015 | |
| 1016 | """Initialize LLMASR4. |
| 1017 | |
| 1018 | Args: |
| 1019 | specaug: TODO. |
| 1020 | specaug_conf: Configuration dict for specaug. |
| 1021 | normalize: TODO. |
| 1022 | normalize_conf: Configuration dict for normalize. |
| 1023 | audio_encoder: TODO. |
| 1024 | audio_encoder_conf: Configuration dict for audio_encoder. |
| 1025 | audio_adaptor: TODO. |
| 1026 | audio_adaptor_conf: Configuration dict for audio_adaptor. |
| 1027 | decoder: TODO. |
| 1028 | decoder_conf: Configuration dict for decoder. |
| 1029 | ctc: TODO. |
| 1030 | ctc_conf: Configuration dict for ctc. |
| 1031 | ctc_weight: TODO. |
| 1032 | llm: TODO. |
| 1033 | llm_conf: Configuration dict for llm. |
| 1034 | input_size: Size/dimension parameter. |
| 1035 | vocab_size: Size/dimension parameter. |
| 1036 | ignore_id: TODO. |
| 1037 | blank_id: TODO. |
nothing calls this directly
no test coverage detected