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