From 71766839fd9ac95a396fa9ae321418d8139255c4 Mon Sep 17 00:00:00 2001
From: hnluo <haoneng.lhn@alibaba-inc.com>
Date: 星期二, 14 二月 2023 15:15:15 +0800
Subject: [PATCH] Merge pull request #106 from alibaba-damo-academy/dev
---
funasr/utils/wav_utils.py | 32 ++++++++++++++++++++++++++++++++
funasr/tasks/abs_task.py | 10 +++++++++-
2 files changed, 41 insertions(+), 1 deletions(-)
diff --git a/funasr/tasks/abs_task.py b/funasr/tasks/abs_task.py
index 02311fd..5be9089 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)
diff --git a/funasr/utils/wav_utils.py b/funasr/utils/wav_utils.py
index 8325ad3..590ccdb 100644
--- a/funasr/utils/wav_utils.py
+++ b/funasr/utils/wav_utils.py
@@ -287,3 +287,35 @@
wav_path = os.path.join(split_dir, str(i + 1), "wav.scp")
text_path = os.path.join(split_dir, str(i + 1), "text")
f_data.write(wav_path + " " + text_path + "\n")
+
+def filter_wav_text(data_dir, dataset):
+ wav_file = os.path.join(data_dir,dataset,"wav.scp")
+ text_file = os.path.join(data_dir, dataset, "text")
+ with open(wav_file) as f_wav, open(text_file) as f_text:
+ wav_lines = f_wav.readlines()
+ text_lines = f_text.readlines()
+ os.rename(wav_file, "{}.bak".format(wav_file))
+ os.rename(text_file, "{}.bak".format(text_file))
+ wav_dict = {}
+ for line in wav_lines:
+ parts = line.strip().split()
+ if len(parts) < 2:
+ continue
+ sample_name, wav_path = parts
+ wav_dict[sample_name] = wav_path
+ text_dict = {}
+ for line in text_lines:
+ parts = line.strip().split(" ", 1)
+ if len(parts) < 2:
+ continue
+ sample_name, txt = parts
+ text_dict[sample_name] = txt
+ filter_count = 0
+ with open(wav_file, "w") as f_wav, open(text_file, "w") as f_text:
+ for sample_name, wav_path in wav_dict.items():
+ if sample_name in text_dict.keys():
+ f_wav.write(sample_name + " " + wav_path + "\n")
+ f_text.write(sample_name + " " + text_dict[sample_name] + "\n")
+ else:
+ filter_count += 1
+ print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))
\ No newline at end of file
--
Gitblit v1.9.1