SentencePieceEncoder

final class fairseq2.data.text.SentencePieceEncoder(model, prefix_tokens=None, suffix_tokens=None, reverse=False, enable_sampling=False, nbest_size=-1, alpha=0.1, device=None, pin_memory=False)[source]

Bases: TextTokenEncoder

__call__(text)[source]

Parameters:: text (str) – The text to encode.
Return type:: Tensor

encode_as_tokens(text)[source]

Parameters:: text (str) – The text to encode.
Return type:: List[str]

property prefix_indices: Tensor | None: Get the indices of the prefix tokens. Shape: \((S)\), where \(S\) is the number of indices.

property suffix_indices: Tensor | None: Get the indices of the suffix tokens. Shape: \((S)\), where \(S\) is the number of indices.