add language model infer pipeline

wucong.lyb

2023-02-10 9e8a52153d1256061ae3f6930a847f6fcad36656

 funasr/datasets/preprocessor.py

@@ -58,6 +58,15 @@
            continue
    return out_txt.strip().split()

def seg_tokenize_wo_pattern(txt, seg_dict):
    out_txt = ""
    for word in txt:
        if word in seg_dict:
            out_txt += seg_dict[word] + " "
        else:
            out_txt += "<unk>" + " "
    return out_txt.strip().split()


def framing(
        x,
@@ -372,6 +381,70 @@
        data = self._text_process(data)
        return data

## FIXME
class LMPreprocessor(CommonPreprocessor):
    def __init__(
            self,
            train: bool,
            token_type: str = None,
            token_list: Union[Path, str, Iterable[str]] = None,
            bpemodel: Union[Path, str, Iterable[str]] = None,
            text_cleaner: Collection[str] = None,
            g2p_type: str = None,
            unk_symbol: str = "<unk>",
            space_symbol: str = "<space>",
            non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
            delimiter: str = None,
            rir_scp: str = None,
            rir_apply_prob: float = 1.0,
            noise_scp: str = None,
            noise_apply_prob: float = 1.0,
            noise_db_range: str = "3_10",
            speech_volume_normalize: float = None,
            speech_name: str = "speech",
            text_name: str = "text",
            split_with_space: bool = False,
            seg_dict_file: str = None,
    ):
        super().__init__(train,
                         token_type,
                         token_list,
                         bpemodel,
                         text_cleaner,
                         g2p_type,
                         unk_symbol,
                         space_symbol,
                         non_linguistic_symbols,
                         delimiter,
                         rir_scp,
                         rir_apply_prob,
                         noise_scp,
                         noise_apply_prob,
                         noise_db_range,
                         speech_volume_normalize,
                         speech_name,
                         text_name,
                         split_with_space,
                         seg_dict_file,
                         )

    def _text_process(
            self, data: Dict[str, Union[str, np.ndarray]]
    ) -> Dict[str, np.ndarray]:
        if self.text_name in data and self.tokenizer is not None:
            text = data[self.text_name]
            text = self.text_cleaner(text)
            if self.split_with_space:
                tokens = text.strip().split(" ")
                if self.seg_dict is not None:
                    tokens = seg_tokenize_wo_pattern(tokens, self.seg_dict)
            else:
                tokens = self.tokenizer.text2tokens(text)
            text_ints = self.token_id_converter.tokens2ids(tokens)
            data[self.text_name] = np.array(text_ints, dtype=np.int64)
        assert check_return_type(data)
        return data


class CommonPreprocessor_multi(AbsPreprocessor):
    def __init__(