Initialize LLMASR. Args: specaug: TODO. specaug_conf: Configuration dict for specaug. normalize: TODO. normalize_conf: Configuration dict for normalize. audio_encoder: TODO. audio_enc
(
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,
)
| 33 | """ |
| 34 | |
| 35 | def __init__( |
| 36 | self, |
| 37 | specaug: str = None, |
| 38 | specaug_conf: dict = None, |
| 39 | normalize: str = None, |
| 40 | normalize_conf: dict = None, |
| 41 | audio_encoder: str = None, |
| 42 | audio_encoder_conf: dict = None, |
| 43 | audio_adaptor: str = None, |
| 44 | audio_adaptor_conf: dict = None, |
| 45 | decoder: str = None, |
| 46 | decoder_conf: dict = None, |
| 47 | ctc: str = None, |
| 48 | ctc_conf: dict = None, |
| 49 | ctc_weight: float = 0.5, |
| 50 | llm: str = None, |
| 51 | llm_conf: dict = None, |
| 52 | input_size: int = 80, |
| 53 | vocab_size: int = -1, |
| 54 | ignore_id: int = -1, |
| 55 | blank_id: int = 0, |
| 56 | sos: int = 1, |
| 57 | eos: int = 2, |
| 58 | lsm_weight: float = 0.0, |
| 59 | length_normalized_loss: bool = False, |
| 60 | report_cer: bool = True, |
| 61 | report_wer: bool = True, |
| 62 | sym_space: str = "<space>", |
| 63 | sym_blank: str = "<blank>", |
| 64 | # extract_feats_in_collect_stats: bool = True, |
| 65 | share_embedding: bool = False, |
| 66 | # preencoder: Optional[AbsPreEncoder] = None, |
| 67 | # postencoder: Optional[AbsPostEncoder] = None, |
| 68 | **kwargs, |
| 69 | ): |
| 70 | |
| 71 | """Initialize LLMASR. |
| 72 | |
| 73 | Args: |
| 74 | specaug: TODO. |
| 75 | specaug_conf: Configuration dict for specaug. |
| 76 | normalize: TODO. |
| 77 | normalize_conf: Configuration dict for normalize. |
| 78 | audio_encoder: TODO. |
| 79 | audio_encoder_conf: Configuration dict for audio_encoder. |
| 80 | audio_adaptor: TODO. |
| 81 | audio_adaptor_conf: Configuration dict for audio_adaptor. |
| 82 | decoder: TODO. |
| 83 | decoder_conf: Configuration dict for decoder. |
| 84 | ctc: TODO. |
| 85 | ctc_conf: Configuration dict for ctc. |
| 86 | ctc_weight: TODO. |
| 87 | llm: TODO. |
| 88 | llm_conf: Configuration dict for llm. |
| 89 | input_size: Size/dimension parameter. |
| 90 | vocab_size: Size/dimension parameter. |
| 91 | ignore_id: TODO. |
| 92 | blank_id: TODO. |
no test coverage detected