From bcf3b486475fbb0a98d62280d47b9c1951368b8c Mon Sep 17 00:00:00 2001
From: haoneng.lhn <haoneng.lhn@alibaba-inc.com>
Date: 星期三, 12 七月 2023 17:57:36 +0800
Subject: [PATCH] fix dataset text filter bug
---
funasr/datasets/large_datasets/dataset.py | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index 1e9bb26..6c166a5 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -229,15 +229,15 @@
mode=mode,
)
- filter_conf = conf.get('filter_conf', {})
- filter_fn = partial(filter, **filter_conf)
- dataset = FilterIterDataPipe(dataset, fn=filter_fn)
-
if "text" in data_names:
vocab = {'vocab': dict, 'seg_dict': seg_dict, 'punc_dict': punc_dict, 'bpe_tokenizer': bpe_tokenizer, 'hw_config': hw_config}
tokenize_fn = partial(tokenize, **vocab)
dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
+ filter_conf = conf.get('filter_conf', {})
+ filter_fn = partial(filter, **filter_conf)
+ dataset = FilterIterDataPipe(dataset, fn=filter_fn)
+
if shuffle:
buffer_conf = conf.get('shuffle_conf', {})
buffer_size = buffer_conf['shuffle_size']
--
Gitblit v1.9.1