Update: added script to handle data and transcribe.

2023-09-20 15:07:25 +02:00
parent dca32539cf
commit 12065e3124
5 changed files with 73 additions and 0 deletions
@@ -0,0 +1,14 @@
+from src.data_handling import download_audio, convert_to_wav
+from src.transcriber import transcribe_wav_file
+
+youtube_links = ['https://www.youtube.com/watch?v=BVVo1BaL6JA', 'https://www.youtube.com/watch?v=m0gr3snccVY&list=PL8p82vzFeTAj3cbHaXE9sC48pm4oZY2rH&index=2', 'https://www.youtube.com/watch?v=ThjgUfck8Sc&list=PL8p82vzFeTAj3cbHaXE9sC48pm4oZY2rH&index=3']
+#youtube_links = ['https://www.youtube.com/watch?v=6A5ZSiosgAk']
+
+for i, link in enumerate(youtube_links):
+    mp4_filename = f"audio_{i+1}.mp4"
+    wav_filename = f"audio_{i+1}.wav"
+
+    download_audio(link, mp4_filename)
+    convert_to_wav(mp4_filename, wav_filename)
+
+    transcribe_wav_file(wav_filename, i)