update cam++ for embed extract

shixian.shi

2024-01-10 668b830cb2a8f69c1cfb131ec9542d27f91b7283

 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: