espnet.st package

Initialize sub package.

espnet.st.__init__

Initialize sub package.

espnet.st.pytorch_backend.st

Training/decoding definition for the speech translation task.

class espnet.st.pytorch_backend.st.CustomConverter(subsampling_factor=1, dtype=torch.float32, use_source_text=False)[source]

Bases: espnet.asr.pytorch_backend.asr.CustomConverter

Custom batch converter for Pytorch.

Parameters:
  • subsampling_factor (int) – The subsampling factor.

  • dtype (torch.dtype) – Data type to convert.

  • use_source_text (bool) – use source transcription.

Construct a CustomConverter object.

espnet.st.pytorch_backend.st.train(args)[source]

Train with the given args.

Parameters:

args (namespace) – The program arguments.

espnet.st.pytorch_backend.st.trans(args)[source]

Decode with the given args.

Parameters:

args (namespace) – The program arguments.

espnet.st.pytorch_backend.__init__

Initialize sub package.