From 65f7cbe9145b81288029d1fe1843778c5c91ce0d Mon Sep 17 00:00:00 2001
From: 嘉渊 <wangjiaming.wjm@alibaba-inc.com>
Date: 星期一, 15 五月 2023 15:24:06 +0800
Subject: [PATCH] update repo
---
funasr/datasets/large_datasets/build_dataloader.py | 13 +++++++++----
1 files changed, 9 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/large_datasets/build_dataloader.py b/funasr/datasets/large_datasets/build_dataloader.py
index 10617e5..f8ee67c 100644
--- a/funasr/datasets/large_datasets/build_dataloader.py
+++ b/funasr/datasets/large_datasets/build_dataloader.py
@@ -66,10 +66,15 @@
class LargeDataLoader(AbsIterFactory):
def __init__(self, args, mode="train"):
- symbol_table = read_symbol_table(args.token_list) if args.token_list is not None else None
- seg_dict = load_seg_dict(args.seg_dict_file) if args.seg_dict_file is not None else None
- punc_dict = load_seg_dict(args.punc_dict_file) if args.punc_dict_file is not None else None
- bpe_tokenizer = load_seg_dict(args.bpemodel_file) if args.bpemodel_file is not None else None
+ symbol_table, seg_dict, punc_dict, bpe_tokenizer = None, None, None, None
+ if hasattr(args, "token_list") and args.token_list is not None:
+ symbol_table = read_symbol_table(args.token_list)
+ if hasattr(args, "seg_dict_file") and args.seg_dict_file is not None:
+ seg_dict = load_seg_dict(args.seg_dict_file)
+ if hasattr(args, "punc_dict_file") and args.punc_dict_file is not None:
+ punc_dict = read_symbol_table(args.punc_dict_file)
+ if hasattr(args, "bpemodel_file") and args.bpemodel_file is not None:
+ bpe_tokenizer = SentencepiecesTokenizer(args.bpemodel_file)
self.dataset_conf = args.dataset_conf
self.frontend_conf = args.frontend_conf
logging.info("dataloader config: {}".format(self.dataset_conf))
--
Gitblit v1.9.1