load_audio_text_image_video

游雁

2024-01-05 e6a7bbe1ca6690faa23d29e22cb74a8d67c09ed3

 funasr/tokenizer/phoneme_tokenizer.py

@@ -13,7 +13,7 @@
from funasr.tokenizer.abs_tokenizer import AbsTokenizer


g2p_choices = [
g2p_classes = [
    None,
    "g2p_en",
    "g2p_en_no_space",
@@ -363,6 +363,7 @@
        non_linguistic_symbols: Union[Path, str, Iterable[str]] = None,
        space_symbol: str = "<space>",
        remove_non_linguistic_symbols: bool = False,
        **kwargs,
    ):
        if g2p_type is None:
            self.g2p = split_by_space