From 3d9f094e9652d4b84894c6fd4eae39a4a753b0f0 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期二, 16 五月 2023 23:48:00 +0800
Subject: [PATCH] train
---
funasr/datasets/large_datasets/build_dataloader.py | 20 ++++++++++++++------
1 files changed, 14 insertions(+), 6 deletions(-)
diff --git a/funasr/datasets/large_datasets/build_dataloader.py b/funasr/datasets/large_datasets/build_dataloader.py
index f1ec005..318ae0b 100644
--- a/funasr/datasets/large_datasets/build_dataloader.py
+++ b/funasr/datasets/large_datasets/build_dataloader.py
@@ -66,16 +66,24 @@
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))
batch_mode = self.dataset_conf.get("batch_mode", "padding")
- self.dataset = Dataset(args.data_list, symbol_table, seg_dict, punc_dict, bpe_tokenizer,
- self.dataset_conf, self.frontend_conf, mode=mode, batch_mode=batch_mode)
+ data_list = args.train_data_file if mode == "train" else args.valid_data_file
+ self.dataset = Dataset(data_list, symbol_table, seg_dict, punc_dict, bpe_tokenizer,
+ self.dataset_conf, self.frontend_conf,
+ speed_perturb=args.speed_perturb if mode == "train" else None,
+ mode=mode, batch_mode=batch_mode)
def build_iter(self, epoch, shuffle=True):
self.dataset.set_epoch(epoch)
--
Gitblit v1.9.1