From fc08b62d05723cdc1ce021bb8ba044ca014fb1f7 Mon Sep 17 00:00:00 2001
From: 游雁 <zhifu.gzf@alibaba-inc.com>
Date: 星期一, 13 三月 2023 18:38:41 +0800
Subject: [PATCH] readme

---
 funasr/utils/wav_utils.py |   16 +++++++++++-----
 1 files changed, 11 insertions(+), 5 deletions(-)

diff --git a/funasr/utils/wav_utils.py b/funasr/utils/wav_utils.py
index afc0ec9..4a764a9 100644
--- a/funasr/utils/wav_utils.py
+++ b/funasr/utils/wav_utils.py
@@ -298,18 +298,24 @@
     os.rename(text_file, "{}.bak".format(text_file))
     wav_dict = {}
     for line in wav_lines:
-        sample_name, wav_path = line.strip().split()
+        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:
-        sample_name, txt = line.strip().split(" ", 1)
-        text_dict[sample_name] = txt
+        parts = line.strip().split()
+        if len(parts) < 2:
+            continue
+        sample_name = parts[0]
+        text_dict[sample_name] = " ".join(parts[1:]).lower()
     filter_count = 0
-    with open(wav_file) as f_wav, open(text_file) as f_text:
+    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
+    print("{}/{} samples in {} are filtered because of the mismatch between wav.scp and text".format(len(wav_lines), filter_count, dataset))

--
Gitblit v1.9.1