def __init__(self, cfg: DecoderConfig, tgt_dict: Dictionary) -> None:
self.tgt_dict = tgt_dict
self.vocab_size = len(tgt_dict)
self.nbest = cfg.nbest
self.unitlm = cfg.unitlm
if cfg.criterion == "ctc":
self.criterion_type = CriterionType.CTC
self.blank = (tgt_dict.index("<ctc_blank>") if "<ctc_blank>"
in tgt_dict.indices else tgt_dict.bos())
if "<sep>" in tgt_dict.indices:
self.silence = tgt_dict.index("<sep>")
elif "|" in tgt_dict.indices:
self.silence = tgt_dict.index("|")
else:
self.silence = tgt_dict.eos()
self.asgtransitions = None
elif cfg.criterion == "asg_loss":
self.criterion_type = CriterionType.ASG
self.blank = -1
self.silence = -1
self.asgtransitions = cfg.asgtransitions
self.maxreplabel = cfg.maxreplabel
assert len(self.asgtransitions) == self.vocab_size**2
else:
raise RuntimeError(f"unknown criterion: {cfg.criterion}")
def __init__(self, bpe, dictionary: Dictionary):
self.bpe = bpe
self.vocab = Vocabulary(
dictionary.symbols,
pad_token=str(dictionary[dictionary.pad()]),
bos_token=str(dictionary[dictionary.bos()]),
eos_token=str(dictionary[dictionary.eos()]),
)
self.bos = self.vocab.bos_token
self.eos = self.vocab.eos_token
def __init__(self, tgt_dict: Dictionary) -> None:
self.tgt_dict = tgt_dict
self.vocab_size = len(tgt_dict)
self.blank = (tgt_dict.index("<ctc_blank>")
if "<ctc_blank>" in tgt_dict.indices else tgt_dict.bos())
if "<sep>" in tgt_dict.indices:
self.silence = tgt_dict.index("<sep>")
elif "|" in tgt_dict.indices:
self.silence = tgt_dict.index("|")
else:
self.silence = tgt_dict.eos()