inference

游雁

2023-05-15 4ac582341c5f88fe30bc47225cf9811cc1233983

 funasr/bin/asr_inference.py

@@ -94,7 +94,7 @@
        frontend = None
        if asr_train_args.frontend is not None and asr_train_args.frontend_conf is not None:
            if asr_train_args.frontend=='wav_frontend':
                frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf).eval()
                frontend = WavFrontend(cmvn_file=cmvn_file, **asr_train_args.frontend_conf)
            else:
                frontend_class=frontend_choices.get_class(asr_train_args.frontend)
                frontend = frontend_class(**asr_train_args.frontend_conf).eval()
@@ -146,13 +146,6 @@
            token_list=token_list,
            pre_beam_score_key=None if ctc_weight == 1.0 else "full",
        )

        beam_search.to(device=device, dtype=getattr(torch, dtype)).eval()
        for scorer in scorers.values():
            if isinstance(scorer, torch.nn.Module):
                scorer.to(device=device, dtype=getattr(torch, dtype)).eval()
        logging.info(f"Beam_search: {beam_search}")
        logging.info(f"Decoding device={device}, dtype={dtype}")

        # 5. [Optional] Build Text converter: e.g. bpe-sym -> Text
        if token_type is None:
@@ -263,70 +256,7 @@
        assert check_return_type(results)
        return results

def inference(
        maxlenratio: float,
        minlenratio: float,
        batch_size: int,
        beam_size: int,
        ngpu: int,
        ctc_weight: float,
        lm_weight: float,
        penalty: float,
        log_level: Union[int, str],
        data_path_and_name_and_type,
        asr_train_config: Optional[str],
        asr_model_file: Optional[str],
        cmvn_file: Optional[str] = None,
        raw_inputs: Union[np.ndarray, torch.Tensor] = None,
        lm_train_config: Optional[str] = None,
        lm_file: Optional[str] = None,
        token_type: Optional[str] = None,
        key_file: Optional[str] = None,
        word_lm_train_config: Optional[str] = None,
        bpemodel: Optional[str] = None,
        allow_variable_data_keys: bool = False,
        streaming: bool = False,
        output_dir: Optional[str] = None,
        dtype: str = "float32",
        seed: int = 0,
        ngram_weight: float = 0.9,
        nbest: int = 1,
        num_workers: int = 1,
        mc: bool = False,
        **kwargs,
):
    inference_pipeline = inference_modelscope(
        maxlenratio=maxlenratio,
        minlenratio=minlenratio,
        batch_size=batch_size,
        beam_size=beam_size,
        ngpu=ngpu,
        ctc_weight=ctc_weight,
        lm_weight=lm_weight,
        penalty=penalty,
        log_level=log_level,
        asr_train_config=asr_train_config,
        asr_model_file=asr_model_file,
        cmvn_file=cmvn_file,
        raw_inputs=raw_inputs,
        lm_train_config=lm_train_config,
        lm_file=lm_file,
        token_type=token_type,
        key_file=key_file,
        word_lm_train_config=word_lm_train_config,
        bpemodel=bpemodel,
        allow_variable_data_keys=allow_variable_data_keys,
        streaming=streaming,
        output_dir=output_dir,
        dtype=dtype,
        seed=seed,
        ngram_weight=ngram_weight,
        nbest=nbest,
        num_workers=num_workers,
        mc=mc,
        **kwargs,
    )
    return inference_pipeline(data_path_and_name_and_type, raw_inputs)


def inference_modelscope(
    maxlenratio: float,