inference

游雁

2023-05-15 4ac582341c5f88fe30bc47225cf9811cc1233983

 funasr/bin/asr_inference.py

@@ -40,6 +40,8 @@
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_none
from funasr.utils import asr_utils, wav_utils, postprocess_utils
from funasr.models.frontend.wav_frontend import WavFrontend
from funasr.tasks.asr import frontend_choices


header_colors = '\033[95m'
@@ -90,6 +92,12 @@
            asr_train_config, asr_model_file, cmvn_file, device
        )
        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)
            else:
                frontend_class=frontend_choices.get_class(asr_train_args.frontend)
                frontend = frontend_class(**asr_train_args.frontend_conf).eval()

        logging.info("asr_model: {}".format(asr_model))
        logging.info("asr_train_args: {}".format(asr_train_args))
@@ -138,13 +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:
@@ -197,12 +198,21 @@

        """
        assert check_argument_types()

        
        # Input as audio signal
        if isinstance(speech, np.ndarray):
            speech = torch.tensor(speech)

        batch = {"speech": speech, "speech_lengths": speech_lengths}
        if self.frontend is not None:
            feats, feats_len = self.frontend.forward(speech, speech_lengths)
            feats = to_device(feats, device=self.device)
            feats_len = feats_len.int()
            self.asr_model.frontend = None
        else:
            feats = speech
            feats_len = speech_lengths
        lfr_factor = max(1, (feats.size()[-1] // 80) - 1)
        batch = {"speech": feats, "speech_lengths": feats_len}

        # a. To device
        batch = to_device(batch, device=self.device)
@@ -246,68 +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,
        **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,
        **kwargs,
    )
    return inference_pipeline(data_path_and_name_and_type, raw_inputs)


def inference_modelscope(
    maxlenratio: float,
@@ -337,6 +286,7 @@
    ngram_weight: float = 0.9,
    nbest: int = 1,
    num_workers: int = 1,
    mc: bool = False,
    param_dict: dict = None,
    **kwargs,
):
@@ -406,7 +356,7 @@
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            mc=True,
            mc=mc,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
@@ -415,7 +365,7 @@
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        

        finish_count = 0
        file_count = 1
        # 7 .Start for-loop