def _get_audio_features()

in whisper/decoding.py [0:0]

• 17 lines of code
• 5 McCabe index (conditional complexity)

    def _get_audio_features(self, mel: Tensor):
        if self.options.fp16:
            mel = mel.half()

        if mel.shape[-2:] == (
            self.model.dims.n_audio_ctx,
            self.model.dims.n_audio_state,
        ):
            # encoded audio features are given; skip audio encoding
            audio_features = mel
        else:
            audio_features = self.model.encoder(mel)

        if audio_features.dtype != (
            torch.float16 if self.options.fp16 else torch.float32
        ):
            return TypeError(
                f"audio_features has an incorrect dtype: {audio_features.dtype}"
            )

        return audio_features