From e90e1b86f10159df42adbdc7e8355ba73ab01f49 Mon Sep 17 00:00:00 2001
From: Plachta <liusongting07@gmail.com>
Date: Mon, 27 Feb 2023 22:05:28 +0800
Subject: [PATCH] updated pipeline

---
 long_audio_transcribe.py  | 1 +
 short_audio_transcribe.py | 1 +
 2 files changed, 2 insertions(+)

diff --git a/long_audio_transcribe.py b/long_audio_transcribe.py
index 2d84c88..af89147 100644
--- a/long_audio_transcribe.py
+++ b/long_audio_transcribe.py
@@ -35,6 +35,7 @@ if __name__ == "__main__":
         lang = result['language']
         if result['language'] not in list(lang2token.keys()):
             print(f"{lang} not supported, ignoring...\n")
+            continue
         # segment audio based on segment results
         character_name = file.rstrip(".wav").split("_")[0]
         code = file.rstrip(".wav").split("_")[1]
diff --git a/short_audio_transcribe.py b/short_audio_transcribe.py
index b642610..f687db9 100644
--- a/short_audio_transcribe.py
+++ b/short_audio_transcribe.py
@@ -67,6 +67,7 @@ if __name__ == "__main__":
                 lang, text = transcribe_one(save_path)
                 if lang not in list(lang2token.keys()):
                     print(f"{lang} not supported, ignoring\n")
+                    continue
                 text = lang2token[lang] + text + lang2token[lang] + "\n"
                 speaker_annos.append(save_path + "|" + speaker + "|" + text)
             except: