espnet2.tts.abs_tts.AbsTTS

source

class espnet2.tts.abs_tts.AbsTTS(*args, **kwargs)

Bases: Module, ABC

TTS abstract class.

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

batch_inference(text: Tensor, text_lengths: Tensor, **kwargs) → Dict[str, Tensor]

Return predicted output for a batch as a dict.

This is an optional method for non-autoregressive models that support batch inference (e.g., FastSpeech, FastSpeech2).

• Parameters:
  • text – Batched input text tensor (B, T_text).
  • text_lengths – Length tensor for batched text (B,).
  • **kwargs – Additional arguments.
• Returns: Dict containing batched outputs.

abstract forward(text: Tensor, text_lengths: Tensor, feats: Tensor, feats_lengths: Tensor, **kwargs) → Tuple[Tensor, Dict[str, Tensor], Tensor]

Calculate outputs and return the loss tensor.

abstract inference(text: Tensor, **kwargs) → Dict[str, Tensor]

Return predicted output as a dict.

property require_raw_speech

Return whether or not raw_speech is required.

property require_vocoder

Return whether or not vocoder is required.