Update app.py

app.py

@@ -37,7 +37,7 @@ def segment_to_dict(segment):
     return segment
 
 def download_video(video_url: str):
-    download_convert_video_to_audio(yt_dlp, video_url, f"/{uuid.uuid4().hex}")
+    download_convert_video_to_audio(yt_dlp, video_url, f"{uuid.uuid4().hex}")
 
 def transcribe_video(video_url: str, beam_size: int = 5, model_size: str = "tiny", word_timestamps: bool = True):
     print("loading model")
@@ -45,12 +45,12 @@ def transcribe_video(video_url: str, beam_size: int = 5, model_size: str = "tiny
     print("getting hex")
     rand_id = uuid.uuid4().hex
     print("doing download")
-    download_convert_video_to_audio(yt_dlp, video_url, f"/{rand_id}")
-    segments, info = model.transcribe(f"/{rand_id}.mp3", beam_size=beam_size, word_timestamps=word_timestamps)
+    download_convert_video_to_audio(yt_dlp, video_url, f"{rand_id}")
+    segments, info = model.transcribe(f"{rand_id}.mp3", beam_size=beam_size, word_timestamps=word_timestamps)
     segments = [segment_to_dict(segment) for segment in segments]
     total_duration = round(info.duration, 2)  # Same precision as the Whisper timestamps.
     print(info)
-    os.remove(f"/{rand_id}.mp3")
+    os.remove(f"{rand_id}.mp3")
     print("Detected language '%s' with probability %f" % (info.language, info.language_probability))
     print(segments)
     return segments