What method do you use to transcribe if you're not debugging or prototyping?

[yonas-g]

As shown in the function below, the documentation mentions that this method is for debugging and prototyping. What method do you suggest to use if you want to deploy?

@torch.no_grad()
    def transcribe(
        self,
        audio: Union[List[str], DataLoader],
        batch_size: int = 4,
        return_hypotheses: bool = False,
        num_workers: int = 0,
        channel_selector: Optional[ChannelSelectorType] = None,
        augmentor: DictConfig = None,
        verbose: bool = True,
    ) -> Union[List[str], List[Hypothesis]]:
        """
        Uses greedy decoding to transcribe audio files. Use this method for debugging and prototyping.