Initialize LLMASR2. 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,
)
| 404 | """ """ |
| 405 | |
| 406 | def __init__( |
| 407 | self, |
| 408 | specaug: str = None, |
| 409 | specaug_conf: dict = None, |
| 410 | normalize: str = None, |
| 411 | normalize_conf: dict = None, |
| 412 | audio_encoder: str = None, |
| 413 | audio_encoder_conf: dict = None, |
| 414 | audio_adaptor: str = None, |
| 415 | audio_adaptor_conf: dict = None, |
| 416 | decoder: str = None, |
| 417 | decoder_conf: dict = None, |
| 418 | ctc: str = None, |
| 419 | ctc_conf: dict = None, |
| 420 | ctc_weight: float = 0.5, |
| 421 | llm: str = None, |
| 422 | llm_conf: dict = None, |
| 423 | input_size: int = 80, |
| 424 | vocab_size: int = -1, |
| 425 | ignore_id: int = -1, |
| 426 | blank_id: int = 0, |
| 427 | sos: int = 1, |
| 428 | eos: int = 2, |
| 429 | lsm_weight: float = 0.0, |
| 430 | length_normalized_loss: bool = False, |
| 431 | report_cer: bool = True, |
| 432 | report_wer: bool = True, |
| 433 | sym_space: str = "<space>", |
| 434 | sym_blank: str = "<blank>", |
| 435 | # extract_feats_in_collect_stats: bool = True, |
| 436 | share_embedding: bool = False, |
| 437 | # preencoder: Optional[AbsPreEncoder] = None, |
| 438 | # postencoder: Optional[AbsPostEncoder] = None, |
| 439 | **kwargs, |
| 440 | ): |
| 441 | |
| 442 | """Initialize LLMASR2. |
| 443 | |
| 444 | Args: |
| 445 | specaug: TODO. |
| 446 | specaug_conf: Configuration dict for specaug. |
| 447 | normalize: TODO. |
| 448 | normalize_conf: Configuration dict for normalize. |
| 449 | audio_encoder: TODO. |
| 450 | audio_encoder_conf: Configuration dict for audio_encoder. |
| 451 | audio_adaptor: TODO. |
| 452 | audio_adaptor_conf: Configuration dict for audio_adaptor. |
| 453 | decoder: TODO. |
| 454 | decoder_conf: Configuration dict for decoder. |
| 455 | ctc: TODO. |
| 456 | ctc_conf: Configuration dict for ctc. |
| 457 | ctc_weight: TODO. |
| 458 | llm: TODO. |
| 459 | llm_conf: Configuration dict for llm. |
| 460 | input_size: Size/dimension parameter. |
| 461 | vocab_size: Size/dimension parameter. |
| 462 | ignore_id: TODO. |
| 463 | blank_id: TODO. |
nothing calls this directly
no test coverage detected