cuda_ctc_decoder¶
- torchaudio.models.decoder.cuda_ctc_decoder(tokens: Union[str, List[str]], nbest: int = 1, beam_size: int = 10, blank_skip_threshold: float = 0.95) CUCTCDecoder [原始碼]¶
建構
CUCTCDecoder
的實例。- 參數:
- 返回:
解碼器
- 返回類型:
- 範例
>>> decoder = cuda_ctc_decoder( >>> vocab_file="tokens.txt", >>> blank_skip_threshold=0.95, >>> ) >>> results = decoder(log_probs, encoder_out_lens) # List of shape (B, nbest) of Hypotheses
- 使用
cuda_ctc_decoder
的教學