add wav/text mismatch process

speech_asr

2023-02-14 f79b6decc9e1cfe7c03d3df4dd673c07d45752d7

add wav/text mismatch process

 funasr/tasks/abs_task.py

@@ -68,7 +68,7 @@
from funasr.utils.types import str2triple_str
from funasr.utils.types import str_or_int
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

try:
@@ -1148,6 +1148,14 @@
                if args.batch_bins is not None:
                    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 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)