Table of Contents

Shortcuts

CUCTCDecoder¶

class torchaudio.models.decoder.CUCTCDecoder[source]¶

Methods¶

Support Structures¶

CUCTCHypothesis¶

class torchaudio.models.decoder.CUCTCHypothesis(tokens: List[int], words: List[str], score: float)[source]¶

Represents hypothesis generated by CUCTC beam search decoder CUCTCDecoder.

tokens: List[int]¶: Predicted sequence of token IDs. Shape (L, ), where L is the length of the output sequence

words: List[str]¶: List of predicted tokens. Algin with modeling unit.

score: float¶: Score corresponding to hypothesis

Docs

Access comprehensive developer documentation for PyTorch

View Docs

Tutorials

Get in-depth tutorials for beginners and advanced developers

View Tutorials

Resources

Find development resources and get your questions answered

View Resources