From 94cb66dbb9ae12e044a41fb8a3d84e1835ee7e7b Mon Sep 17 00:00:00 2001
From: zhifu gao <zhifu.gzf@alibaba-inc.com>
Date: 星期四, 02 三月 2023 20:20:10 +0800
Subject: [PATCH] Merge pull request #177 from alibaba-damo-academy/dev_timestamp
---
funasr/tasks/abs_task.py | 16 ++++++++++++++--
1 files changed, 14 insertions(+), 2 deletions(-)
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index 02311fd..a643acb 100644
--- a/funasr/tasks/abs_task.py
+++ b/funasr/tasks/abs_task.py
@@ -71,7 +71,7 @@
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:
@@ -1153,6 +1153,14 @@
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)
@@ -1340,12 +1348,16 @@
if args.dataset_type == "large":
from funasr.datasets.large_datasets.build_dataloader import ArkDataLoader
train_iter_factory = ArkDataLoader(args.train_data_file, args.token_list, args.dataset_conf,
+ frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
seg_dict_file=args.seg_dict_file if hasattr(args,
"seg_dict_file") else None,
+ punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
mode="train")
- valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
+ valid_iter_factory = ArkDataLoader(args.valid_data_file, args.token_list, args.dataset_conf,
+ frontend_conf=args.frontend_conf if hasattr(args, "frontend_conf") else None,
seg_dict_file=args.seg_dict_file if hasattr(args,
"seg_dict_file") else None,
+ punc_dict_file=args.punc_list if hasattr(args, "punc_list") else None,
mode="eval")
elif args.dataset_type == "small":
train_iter_factory = cls.build_iter_factory(
--
Gitblit v1.9.1