Fix invalid escape sequence '\w' in RegEx due to 'r' missing (#1967)

Ziyao Wang

2024-07-29 9f04fd130c8436b5a23c4c334d8fb7ea11a95ba6

 funasr/tokenizer/build_tokenizer.py

@@ -1,17 +1,7 @@
from pathlib import Path
from typing import Iterable
from typing import Union
from abc import ABC
from abc import abstractmethod
from typing import Iterable
from typing import List
from pathlib import Path
from typing import Dict
from typing import Iterable
from typing import List
from typing import Union

import numpy as np

from funasr.tokenizer.abs_tokenizer import AbsTokenizer
from funasr.tokenizer.char_tokenizer import CharTokenizer
@@ -28,7 +18,6 @@
    space_symbol: str = "<space>",
    delimiter: str = None,
    g2p_type: str = None,
    **kwargs,
) -> AbsTokenizer:
    """A helper function to instantiate Tokenizer"""
    if token_type == "bpe":
@@ -39,7 +28,7 @@
            raise RuntimeError(
                "remove_non_linguistic_symbols is not implemented for token_type=bpe"
            )
        return SentencepiecesTokenizer(bpemodel, **kwargs)
        return SentencepiecesTokenizer(bpemodel)

    elif token_type == "word":
        if remove_non_linguistic_symbols and non_linguistic_symbols is not None:
@@ -49,14 +38,13 @@
                remove_non_linguistic_symbols=True,
            )
        else:
            return WordTokenizer(delimiter=delimiter, **kwargs)
            return WordTokenizer(delimiter=delimiter)

    elif token_type == "char":
        return CharTokenizer(
            non_linguistic_symbols=non_linguistic_symbols,
            space_symbol=space_symbol,
            remove_non_linguistic_symbols=remove_non_linguistic_symbols,
            **kwargs
        )

    elif token_type == "phn":
@@ -65,10 +53,7 @@
            non_linguistic_symbols=non_linguistic_symbols,
            space_symbol=space_symbol,
            remove_non_linguistic_symbols=remove_non_linguistic_symbols,
            **kwargs
        )

    else:
        raise ValueError(
            f"token_mode must be one of bpe, word, char or phn: " f"{token_type}"
        )
        raise ValueError(f"token_mode must be one of bpe, word, char or phn: " f"{token_type}")