From e180abe4fddaeba9a6490dfc91d99f55e9b9fccd Mon Sep 17 00:00:00 2001
From: speech_asr <wangjiaming.wjm@alibaba-inc.com>
Date: 星期二, 14 二月 2023 14:39:45 +0800
Subject: [PATCH] update docs

---
 funasr/utils/wav_utils.py |   26 ++++++++++++++++++++++++++
 1 files changed, 26 insertions(+), 0 deletions(-)

diff --git a/funasr/utils/wav_utils.py b/funasr/utils/wav_utils.py
index 8325ad3..afc0ec9 100644
--- a/funasr/utils/wav_utils.py
+++ b/funasr/utils/wav_utils.py
@@ -287,3 +287,29 @@
             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:
+        sample_name, wav_path = line.strip().split()
+        wav_dict[sample_name] = wav_path
+    text_dict = {}
+    for line in text_lines:
+        sample_name, txt = line.strip().split(" ", 1)
+        text_dict[sample_name] = txt
+    filter_count = 0
+    with open(wav_file) as f_wav, open(text_file) 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