From 0a4e3b7e64e9e095cfdcd4b3c28bde7aa58839e7 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期六, 11 二月 2023 17:40:00 +0800
Subject: [PATCH] readme
---
funasr/datasets/large_datasets/dataset.py | 7 ++++---
1 files changed, 4 insertions(+), 3 deletions(-)
diff --git a/funasr/datasets/large_datasets/dataset.py b/funasr/datasets/large_datasets/dataset.py
index 2d3ffd5..55b0678 100644
--- a/funasr/datasets/large_datasets/dataset.py
+++ b/funasr/datasets/large_datasets/dataset.py
@@ -158,9 +158,10 @@
filter_fn = partial(filter, **filter_conf)
dataset = FilterIterDataPipe(dataset, fn=filter_fn)
- vocab = {'vocab': dict, 'seg_dict': seg_dict}
- tokenize_fn = partial(tokenize, **vocab)
- dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
+ if "text" in data_names:
+ vocab = {'vocab': dict, 'seg_dict': seg_dict}
+ tokenize_fn = partial(tokenize, **vocab)
+ dataset = MapperIterDataPipe(dataset, fn=tokenize_fn)
if shuffle:
buffer_conf = conf.get('shuffle_conf', {})
--
Gitblit v1.9.1