inference

游雁

2023-05-16 0271fbe4fd11114c259ec970b1b04938010a16e3

 funasr/bin/asr_inference_launch.py

@@ -77,6 +77,7 @@
from funasr.bin.punc_infer import Text2Punc
from funasr.bin.tp_infer import Speech2Timestamp
from funasr.bin.asr_infer import Speech2TextTransducer
from funasr.bin.asr_infer import Speech2TextSAASR

def inference_asr(
    maxlenratio: float,
@@ -1444,6 +1445,167 @@
    return _forward


def inference_sa_asr(
    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,
    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,
    param_dict: dict = None,
    **kwargs,
):
    assert check_argument_types()
    if batch_size > 1:
        raise NotImplementedError("batch decoding is not implemented")
    if word_lm_train_config is not None:
        raise NotImplementedError("Word LM is not implemented")
    if ngpu > 1:
        raise NotImplementedError("only single GPU decoding is supported")
    
    for handler in logging.root.handlers[:]:
        logging.root.removeHandler(handler)
    
    logging.basicConfig(
        level=log_level,
        format="%(asctime)s (%(module)s:%(lineno)d) %(levelname)s: %(message)s",
    )
    
    if ngpu >= 1 and torch.cuda.is_available():
        device = "cuda"
    else:
        device = "cpu"
    
    # 1. Set random-seed
    set_all_random_seed(seed)
    
    # 2. Build speech2text
    speech2text_kwargs = dict(
        asr_train_config=asr_train_config,
        asr_model_file=asr_model_file,
        cmvn_file=cmvn_file,
        lm_train_config=lm_train_config,
        lm_file=lm_file,
        token_type=token_type,
        bpemodel=bpemodel,
        device=device,
        maxlenratio=maxlenratio,
        minlenratio=minlenratio,
        dtype=dtype,
        beam_size=beam_size,
        ctc_weight=ctc_weight,
        lm_weight=lm_weight,
        ngram_weight=ngram_weight,
        penalty=penalty,
        nbest=nbest,
        streaming=streaming,
    )
    logging.info("speech2text_kwargs: {}".format(speech2text_kwargs))
    speech2text = Speech2TextSAASR(**speech2text_kwargs)
    
    def _forward(data_path_and_name_and_type,
                 raw_inputs: Union[np.ndarray, torch.Tensor] = None,
                 output_dir_v2: Optional[str] = None,
                 fs: dict = None,
                 param_dict: dict = None,
                 **kwargs,
                 ):
        # 3. Build data-iterator
        if data_path_and_name_and_type is None and raw_inputs is not None:
            if isinstance(raw_inputs, torch.Tensor):
                raw_inputs = raw_inputs.numpy()
            data_path_and_name_and_type = [raw_inputs, "speech", "waveform"]
        loader = ASRTask.build_streaming_iterator(
            data_path_and_name_and_type,
            dtype=dtype,
            fs=fs,
            mc=mc,
            batch_size=batch_size,
            key_file=key_file,
            num_workers=num_workers,
            preprocess_fn=ASRTask.build_preprocess_fn(speech2text.asr_train_args, False),
            collate_fn=ASRTask.build_collate_fn(speech2text.asr_train_args, False),
            allow_variable_data_keys=allow_variable_data_keys,
            inference=True,
        )
        
        finish_count = 0
        file_count = 1
        # 7 .Start for-loop
        # FIXME(kamo): The output format should be discussed about
        asr_result_list = []
        output_path = output_dir_v2 if output_dir_v2 is not None else output_dir
        if output_path is not None:
            writer = DatadirWriter(output_path)
        else:
            writer = None
        
        for keys, batch in loader:
            assert isinstance(batch, dict), type(batch)
            assert all(isinstance(s, str) for s in keys), keys
            _bs = len(next(iter(batch.values())))
            assert len(keys) == _bs, f"{len(keys)} != {_bs}"
            # batch = {k: v[0] for k, v in batch.items() if not k.endswith("_lengths")}
            # N-best list of (text, token, token_int, hyp_object)
            try:
                results = speech2text(**batch)
            except TooShortUttError as e:
                logging.warning(f"Utterance {keys} {e}")
                hyp = Hypothesis(score=0.0, scores={}, states={}, yseq=[])
                results = [[" ", ["sil"], [2], hyp]] * nbest
            
            # Only supporting batch_size==1
            key = keys[0]
            for n, (text, text_id, token, token_int, hyp) in zip(range(1, nbest + 1), results):
                # Create a directory: outdir/{n}best_recog
                if writer is not None:
                    ibest_writer = writer[f"{n}best_recog"]
                    
                    # Write the result to each file
                    ibest_writer["token"][key] = " ".join(token)
                    ibest_writer["token_int"][key] = " ".join(map(str, token_int))
                    ibest_writer["score"][key] = str(hyp.score)
                    ibest_writer["text_id"][key] = text_id
                
                if text is not None:
                    text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                    item = {'key': key, 'value': text_postprocessed}
                    asr_result_list.append(item)
                    finish_count += 1
                    asr_utils.print_progress(finish_count / file_count)
                    if writer is not None:
                        ibest_writer["text"][key] = text
                
                logging.info("uttid: {}".format(key))
                logging.info("text predictions: {}".format(text))
                logging.info("text_id predictions: {}\n".format(text_id))
        return asr_result_list
    
    return _forward


def inference_launch(**kwargs):
    if 'mode' in kwargs:
        mode = kwargs['mode']
@@ -1464,6 +1626,8 @@
        return inference_mfcca(**kwargs)
    elif mode == "rnnt":
        return inference_transducer(**kwargs)
    elif mode == "sa_asr":
        return inference_sa_asr(**kwargs)
    else:
        logging.info("Unknown decoding mode: {}".format(mode))
        return None