From 70645e48072bf193fbf069949f1d2b10fddac8a3 Mon Sep 17 00:00:00 2001
From: pointerhacker <145901472+pointerhacker@users.noreply.github.com>
Date: 星期二, 15 十月 2024 17:50:51 +0800
Subject: [PATCH] 数据并行可能导致的模型训练报错 (#2139)
---
funasr/tokenizer/sentencepiece_tokenizer.py | 6 ++++++
1 files changed, 6 insertions(+), 0 deletions(-)
diff --git a/funasr/tokenizer/sentencepiece_tokenizer.py b/funasr/tokenizer/sentencepiece_tokenizer.py
index 1be1b81..0b47a9f 100644
--- a/funasr/tokenizer/sentencepiece_tokenizer.py
+++ b/funasr/tokenizer/sentencepiece_tokenizer.py
@@ -49,3 +49,9 @@
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