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

add wav/text mismatch process

Browse Source
This commit is contained in:
speech_asr 2023-02-14 14:43:25 +08:00
parent e180abe4fd
commit f79b6decc9
1 changed files with 9 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
funasr/tasks/abs_task.py
View File

@ -68,7 +68,7 @@ from funasr.utils.types import str2bool
from funasr.utils.types import str2triple_str from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_int from funasr.utils.types import str_or_int
from funasr.utils.types import str_or_none from funasr.utils.types import str_or_none
from funasr.utils.wav_utils import calc_shape, generate_data_list from funasr.utils.wav_utils import calc_shape, generate_data_list, filter_wav_text
from funasr.utils.yaml_no_alias_safe_dump import yaml_no_alias_safe_dump from funasr.utils.yaml_no_alias_safe_dump import yaml_no_alias_safe_dump
try: try:
@ -1148,6 +1148,14 @@ class AbsTask(ABC):
if args.batch_bins is not None: if args.batch_bins is not None:
args.batch_bins = args.batch_bins * args.ngpu args.batch_bins = args.batch_bins * args.ngpu
# filter samples if wav.scp and text are mismatch
if (args.train_shape_file is None and args.dataset_type == "small") or args.train_data_file is None and args.dataset_type == "large":
if not args.simple_ddp or distributed_option.dist_rank == 0:
filter_wav_text(args.data_dir, args.train_set)
filter_wav_text(args.data_dir, args.dev_set)
if args.simple_ddp:
dist.barrier()
if args.train_shape_file is None and args.dataset_type == "small": if args.train_shape_file is None and args.dataset_type == "small":
if not args.simple_ddp or distributed_option.dist_rank == 0: if not args.simple_ddp or distributed_option.dist_rank == 0:
calc_shape(args.data_dir, args.train_set, args.frontend_conf, args.speech_length_min, args.speech_length_max) calc_shape(args.data_dir, args.train_set, args.frontend_conf, args.speech_length_min, args.speech_length_max)