update with main (#1163)

zhifu gao

2023-12-11 85cabd30a9185cf5bebde4a6415a122142ea3b43

 funasr/tokenizer/build_tokenizer.py

@@ -1,7 +1,17 @@
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
@@ -18,7 +28,8 @@
    space_symbol: str = "<space>",
    delimiter: str = None,
    g2p_type: str = None,
) -> AbsTokenizer:
    **kwargs,
):
    """A helper function to instantiate Tokenizer"""
    if token_type == "bpe":
        if bpemodel is None:
@@ -28,7 +39,7 @@
            raise RuntimeError(
                "remove_non_linguistic_symbols is not implemented for token_type=bpe"
            )
        return SentencepiecesTokenizer(bpemodel)
        return SentencepiecesTokenizer(bpemodel, **kwargs)

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

    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":
@@ -53,6 +65,7 @@
            non_linguistic_symbols=non_linguistic_symbols,
            space_symbol=space_symbol,
            remove_non_linguistic_symbols=remove_non_linguistic_symbols,
            **kwargs
        )

    else: