Funasr1.0 (#1279)

zhifu gao

2024-01-22 3919d7454c070702e94b149e4032e9db08d28fa3

Funasr1.0 (#1279)

* funasr1.0 update

* funasr1.0 paraformer-en

 .gitignore

@@ -23,3 +23,4 @@
.ipynb_checkpoints
outputs*
emotion2vec*
GPT-SoVITS*

 funasr/models/paraformer/model.py

@@ -528,9 +528,9 @@
                if tokenizer is not None:
                    # Change integer-ids to tokens
                    token = tokenizer.ids2tokens(token_int)
                    text = tokenizer.tokens2text(token)
                    
                    text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                    text_postprocessed = tokenizer.tokens2text(token)
                    if not hasattr(tokenizer, "bpemodel"):
                        text_postprocessed, _ = postprocess_utils.sentence_postprocess(token)
                    
                    result_i = {"key": key[i], "text": text_postprocessed}


 funasr/tokenizer/sentencepiece_tokenizer.py

@@ -5,12 +5,16 @@

import sentencepiece as spm

from funasr.tokenizer.abs_tokenizer import AbsTokenizer
from funasr.tokenizer.abs_tokenizer import BaseTokenizer
from funasr.register import tables


class SentencepiecesTokenizer(AbsTokenizer):
    def __init__(self, model: Union[Path, str]):
        self.model = str(model)
@tables.register("tokenizer_classes", "SentencepiecesTokenizer")
class SentencepiecesTokenizer(BaseTokenizer):
    def __init__(self, bpemodel: Union[Path, str],
                 **kwargs
                 ):
        super().__init__(**kwargs)
        self.bpemodel = str(bpemodel)
        # NOTE(kamo):
        # Don't build SentencePieceProcessor in __init__()
        # because it's not picklable and it may cause following error,
@@ -19,13 +23,13 @@
        self.sp = None

    def __repr__(self):
        return f'{self.__class__.__name__}(model="{self.model}")'
        return f'{self.__class__.__name__}(model="{self.bpemodel}")'

    def _build_sentence_piece_processor(self):
        # Build SentencePieceProcessor lazily.
        if self.sp is None:
            self.sp = spm.SentencePieceProcessor()
            self.sp.load(self.model)
            self.sp.load(self.bpemodel)

    def text2tokens(self, line: str) -> List[str]:
        self._build_sentence_piece_processor()
@@ -34,3 +38,11 @@
    def tokens2text(self, tokens: Iterable[str]) -> str:
        self._build_sentence_piece_processor()
        return self.sp.DecodePieces(list(tokens))

    def encode(self, line: str) -> List[int]:
        self._build_sentence_piece_processor()
        return self.sp.EncodeAsIds(line)

    def decode(self, line: List[int]):
        self._build_sentence_piece_processor()
        return self.sp.DecodeIds(line)