From b5d3df75cf6462aa3bf42fd3c86fa2aa7f1c8a15 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期五, 24 十一月 2023 00:54:44 +0800
Subject: [PATCH] setup jamo
---
funasr/datasets/large_datasets/build_dataloader.py | 11 +++++++----
1 files changed, 7 insertions(+), 4 deletions(-)
diff --git a/funasr/datasets/large_datasets/build_dataloader.py b/funasr/datasets/large_datasets/build_dataloader.py
index 7a1a906..134b20a 100644
--- a/funasr/datasets/large_datasets/build_dataloader.py
+++ b/funasr/datasets/large_datasets/build_dataloader.py
@@ -9,7 +9,7 @@
from funasr.datasets.large_datasets.dataset import Dataset
from funasr.iterators.abs_iter_factory import AbsIterFactory
-from funasr.text.abs_tokenizer import AbsTokenizer
+from funasr.tokenizer.abs_tokenizer import AbsTokenizer
def read_symbol_table(symbol_table_file):
@@ -69,12 +69,15 @@
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, "punc_list") and args.punc_list is not None:
+ punc_dict = read_symbol_table(args.punc_list)
if hasattr(args, "bpemodel") and args.bpemodel is not None:
bpe_tokenizer = SentencepiecesTokenizer(args.bpemodel)
self.dataset_conf = args.dataset_conf
- self.frontend_conf = args.frontend_conf
+ if "frontend_conf" not in args:
+ self.frontend_conf = None
+ else:
+ self.frontend_conf = args.frontend_conf
self.speed_perturb = args.speed_perturb if hasattr(args, "speed_perturb") else None
logging.info("dataloader config: {}".format(self.dataset_conf))
batch_mode = self.dataset_conf.get("batch_mode", "padding")
--
Gitblit v1.9.1