Initial commit: media-to-text app

2026-02-08 23:26:40 +08:00
commit b155e85040
44 changed files with 1396 additions and 0 deletions
@@ -0,0 +1,13 @@
+#!/usr/bin/env python3
+import sys
+import whisper
+
+if len(sys.argv) < 2:
+    print("Usage: python transcribe.py <audio_or_video_file> [language]")
+    print("Example: python transcribe.py audio.mp3 es")
+    sys.exit(1)
+
+model = whisper.load_model("base")
+language = sys.argv[2] if len(sys.argv) > 2 else None
+result = model.transcribe(sys.argv[1], language=language)
+print(result["text"])