From 33d3d2084403fd34b79c835d2f2fe04f6cd8f738 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期三, 13 九月 2023 09:33:54 +0800
Subject: [PATCH] Merge branch 'main' of github.com:alibaba-damo-academy/FunASR add
---
funasr/datasets/large_datasets/build_dataloader.py | 18 ++++++++++--------
1 files changed, 10 insertions(+), 8 deletions(-)
diff --git a/funasr/datasets/large_datasets/build_dataloader.py b/funasr/datasets/large_datasets/build_dataloader.py
index 318ae0b..6c2da2a 100644
--- a/funasr/datasets/large_datasets/build_dataloader.py
+++ b/funasr/datasets/large_datasets/build_dataloader.py
@@ -6,7 +6,6 @@
import sentencepiece as spm
from torch.utils.data import DataLoader
-from typeguard import check_argument_types
from funasr.datasets.large_datasets.dataset import Dataset
from funasr.iterators.abs_iter_factory import AbsIterFactory
@@ -43,7 +42,6 @@
class SentencepiecesTokenizer(AbsTokenizer):
def __init__(self, model: Union[Path, str]):
- assert check_argument_types()
self.model = str(model)
self.sp = None
@@ -71,18 +69,22 @@
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)
+ 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")
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,
+ speed_perturb=self.speed_perturb if mode == "train" else None,
mode=mode, batch_mode=batch_mode)
def build_iter(self, epoch, shuffle=True):
--
Gitblit v1.9.1