speech_recognition/FunASR
1
0
Fork 0
mirror of https://github.com/modelscope/FunASR synced 2025-09-15 14:48:36 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

update

Browse Source
This commit is contained in:
嘉渊 2023-04-25 16:33:00 +08:00
parent 7436acc5dd
commit 6e66a74ae6
1 changed files with 3 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
funasr/utils/prepare_data.py
View File

@ -115,7 +115,7 @@ def calc_shape(args, dataset, nj=32):
logging.info('Generating shape files done.') logging.info('Generating shape files done.')
def generate_data_list(data_dir, dataset, nj=100): def generate_data_list(data_dir, dataset, nj=32):
list_file = os.path.join(data_dir, dataset, "data.list") list_file = os.path.join(data_dir, dataset, "data.list")
if os.path.exists(list_file): if os.path.exists(list_file):
logging.info('Data list for large dataset already exists.') logging.info('Data list for large dataset already exists.')
@ -160,11 +160,11 @@ def prepare_data(args, distributed_option):
filter_wav_text(args.data_dir, args.train_set) filter_wav_text(args.data_dir, args.train_set)
filter_wav_text(args.data_dir, args.valid_set) filter_wav_text(args.data_dir, args.valid_set)
if args.dataset_type == "small" and args.train_shape_file is None: if args.dataset_type == "small":
calc_shape(args, args.train_set) calc_shape(args, args.train_set)
calc_shape(args, args.valid_set) calc_shape(args, args.valid_set)
if args.dataset_type == "large" and args.train_data_file is None: if args.dataset_type == "large":
generate_data_list(args.data_dir, args.train_set) generate_data_list(args.data_dir, args.train_set)
generate_data_list(args.data_dir, args.valid_set) generate_data_list(args.data_dir, args.valid_set)