espnet2.asr.encoder.whisper_encoder.OpenAIWhisperEncoder

source

class espnet2.asr.encoder.whisper_encoder.OpenAIWhisperEncoder(input_size: int = 1, dropout_rate: float = 0.0, whisper_model: str = 'small', download_dir: str | None = None, use_specaug: bool = False, specaug_conf: dict | None = None, do_pad_trim: bool = False)

Bases: AbsEncoder

Transformer-based Speech Encoder from OpenAI’s Whisper Model:

URL: https://github.com/openai/whisper

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

forward(xs_pad: Tensor, ilens: Tensor, prev_states: Tensor | None = None) → Tuple[Tensor, Tensor, Tensor | None]

Defines the computation performed at every call.

Should be overridden by all subclasses.

NOTE

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.

log_mel_spectrogram(audio: Tensor, ilens: Tensor | None = None) → Tensor

Use log-mel spectrogram computation native to Whisper training

output_size() → int

pad_or_trim(array: Tensor, length: int, axis: int = -1) → Tensor

Pad or trim the audio array to N_SAMPLES.

Used in zero-shot inference cases.

whisper_encode(input: Tensor, ilens: Tensor | None = None) → Tensor