From 6e69d784e4814c3dbe35e8f70c6cf4b920c8b20b Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 19 三月 2025 23:10:13 +0800
Subject: [PATCH] 1. bug fix:list(mean)和list(var)，由于mean和var是numpy，导致写入到文件的格式错误，参考上面的话，大概率是list(mean.tolist())，其实外层list没有必要 (#2437)
---
funasr/tokenizer/sentencepiece_tokenizer.py | 21 +++++++++++++++------
1 files changed, 15 insertions(+), 6 deletions(-)
diff --git a/funasr/tokenizer/sentencepiece_tokenizer.py b/funasr/tokenizer/sentencepiece_tokenizer.py
index 05ca348..0b47a9f 100644
--- a/funasr/tokenizer/sentencepiece_tokenizer.py
+++ b/funasr/tokenizer/sentencepiece_tokenizer.py
@@ -8,11 +8,10 @@
from funasr.tokenizer.abs_tokenizer import BaseTokenizer
from funasr.register import tables
+
@tables.register("tokenizer_classes", "SentencepiecesTokenizer")
class SentencepiecesTokenizer(BaseTokenizer):
- def __init__(self, bpemodel: Union[Path, str],
- **kwargs
- ):
+ def __init__(self, bpemodel: Union[Path, str], **kwargs):
super().__init__(**kwargs)
self.bpemodel = str(bpemodel)
# NOTE(kamo):
@@ -21,6 +20,7 @@
# "TypeError: can't pickle SwigPyObject objects",
# when giving it as argument of "multiprocessing.Process()".
self.sp = None
+ self._build_sentence_piece_processor()
def __repr__(self):
return f'{self.__class__.__name__}(model="{self.bpemodel}")'
@@ -39,10 +39,19 @@
self._build_sentence_piece_processor()
return self.sp.DecodePieces(list(tokens))
- def encode(self, line: str) -> List[int]:
+ def encode(self, line: str, **kwargs) -> List[int]:
self._build_sentence_piece_processor()
return self.sp.EncodeAsIds(line)
- def decode(self, line: List[int]):
+ def decode(self, line: List[int], **kwargs):
self._build_sentence_piece_processor()
- return self.sp.DecodeIds(line)
\ No newline at end of file
+ return self.sp.DecodeIds(line)
+
+ def get_vocab_size(self):
+ return self.sp.GetPieceSize()
+
+ def ids2tokens(self, *args, **kwargs):
+ return self.decode(*args, **kwargs)
+
+ def tokens2ids(self, *args, **kwargs):
+ return self.encode(*args, **kwargs)
--
Gitblit v1.9.1