From e24dbdc496debec225414d4d2c760f5775e64f2a Mon Sep 17 00:00:00 2001
From: 天地 <tiandiweizun@gmail.com>
Date: 星期三, 26 三月 2025 13:44:41 +0800
Subject: [PATCH] 感觉应该从文件读取更合适，因为上面判断了文件存在，且可以读取，如果本身是文本的话，下面也会有逻辑进行处理 (#2452)
---
funasr/download/download_dataset_from_hub.py | 19 +++++++++++--------
1 files changed, 11 insertions(+), 8 deletions(-)
diff --git a/funasr/download/download_dataset_from_hub.py b/funasr/download/download_dataset_from_hub.py
index d06d821..2419ce8 100644
--- a/funasr/download/download_dataset_from_hub.py
+++ b/funasr/download/download_dataset_from_hub.py
@@ -1,11 +1,14 @@
-
def download_dataset():
- pass
+ pass
+
def download_dataset_from_ms(**kwargs):
- from modelscope.msdatasets import MsDataset
- dataset_name = kwargs.get("dataset_name", 'speech_asr/speech_asr_aishell1_trainsets')
- subset_name = kwargs.get("subset_name", 'default')
- split = kwargs.get("split", 'train')
- data_dump_dir = kwargs.get("data_dump_dir", None)
- ds = MsDataset.load(dataset_name=dataset_name, subset_name=subset_name, split=split, cache_dir=data_dump_dir)
\ No newline at end of file
+ from modelscope.msdatasets import MsDataset
+
+ dataset_name = kwargs.get("dataset_name", "speech_asr/speech_asr_aishell1_trainsets")
+ subset_name = kwargs.get("subset_name", "default")
+ split = kwargs.get("split", "train")
+ data_dump_dir = kwargs.get("data_dump_dir", None)
+ ds = MsDataset.load(
+ dataset_name=dataset_name, subset_name=subset_name, split=split, cache_dir=data_dump_dir
+ )
--
Gitblit v1.9.1