espnet2.text.whisper_tokenizer.OpenAIWhisperTokenizer

source

class espnet2.text.whisper_tokenizer.OpenAIWhisperTokenizer(model_type: str, language: str = 'en', task: str = 'transcribe', sot: bool = False, speaker_change_symbol: str = '<sc>', added_tokens_txt: str | None = None)

Bases: AbsTokenizer

text2tokens(line: str) → List[str]

tokens2text(tokens: Iterable[str]) → str