espnet2.speechlm.tokenizer.beats_tokenizer.BeatsRandomTokenizer

source

class espnet2.speechlm.tokenizer.beats_tokenizer.BeatsRandomTokenizer(tokenizer_config: Dict | None = None, fbank_mean: float = 15.41663, fbank_std: float = 6.55582)

Bases: Module

Initializes internal Module state, shared by both nn.Module and ScriptModule.

encode(xs_pad: Tensor, ilens: Tensor | None = None)

forward(xs_pad: Tensor)

• Parameters:xs_pad (torch.Tensor) – Input tensor (B, T).

frontend(source: Tensor) → Tensor

Preprocess raw audio.