Update app.py

app.py

@@ -25,14 +25,15 @@ print("Model successfully loaded.")
 def generate_unique_filename(extension):
     return f"{uuid.uuid4()}{extension}"
 
-def cleanup_file(file_path):
-    if os.path.exists(file_path):
-        os.remove(file_path)
-        print(f"Cleaned up file: {file_path}")
+def cleanup_files(*files):
+    for file in files:
+        if file and os.path.exists(file):
+            os.remove(file)
+            print(f"Removed file: {file}")
 
 def download_youtube_audio(url):
     print(f"Downloading audio from YouTube: {url}")
-    output_path = generate_unique_filename('.wav')
+    output_path = generate_unique_filename(".wav")
     ydl_opts = {
         'format': 'bestaudio/best',
         'postprocessors': [{
@@ -41,41 +42,36 @@ def download_youtube_audio(url):
         }],
         'outtmpl': output_path
     }
-    try:
-        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-            ydl.download([url])
-        
-        if os.path.exists(output_path):
-            print(f"Audio download completed. File saved at: {output_path}")
-            print(f"File size: {os.path.getsize(output_path)} bytes")
-            return output_path
-        else:
-            print(f"Error: File {output_path} not found after download.")
-            return None
-    except Exception as e:
-        print(f"Error downloading YouTube audio: {e}")
-        return None
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        ydl.download([url])
+    
+    if os.path.exists(output_path):
+        print(f"Audio download completed. File saved at: {output_path}")
+        print(f"File size: {os.path.getsize(output_path)} bytes")
+    else:
+        print(f"Error: File {output_path} not found after download.")
+    
+    return output_path
 
 @spaces.GPU(duration=60)
 def transcribe_audio(file_path):
     print(f"Starting transcription of file: {file_path}")
-    if not os.path.exists(file_path):
-        print(f"Error: File {file_path} does not exist.")
-        return None
-
+    temp_audio = None
     if file_path.endswith(('.mp4', '.avi', '.mov', '.flv')):
         print("Video file detected. Extracting audio...")
         try:
             video = mp.VideoFileClip(file_path)
-            audio_path = generate_unique_filename('.wav')
-            video.audio.write_audiofile(audio_path)
-            cleanup_file(file_path)
-            file_path = audio_path
+            temp_audio = generate_unique_filename(".wav")
+            video.audio.write_audiofile(temp_audio)
+            file_path = temp_audio
         except Exception as e:
             print(f"Error extracting audio from video: {e}")
-            return None
-
-    output_file = generate_unique_filename('.json')
+            raise
+    
+    print(f"Does the file exist? {os.path.exists(file_path)}")
+    print(f"File size: {os.path.getsize(file_path) if os.path.exists(file_path) else 'N/A'} bytes")
+    
+    output_file = generate_unique_filename(".json")
     command = [
         "insanely-fast-whisper",
         "--file-name", file_path,
@@ -94,32 +90,34 @@ def transcribe_audio(file_path):
         print(f"Error running insanely-fast-whisper: {e}")
         print(f"Standard output: {e.stdout}")
         print(f"Error output: {e.stderr}")
-        cleanup_file(file_path)
-        cleanup_file(output_file)
-        return None
-
+        raise
+    
+    print(f"Reading transcription file: {output_file}")
     try:
         with open(output_file, "r") as f:
             transcription = json.load(f)
     except json.JSONDecodeError as e:
         print(f"Error decoding JSON: {e}")
-        cleanup_file(file_path)
-        cleanup_file(output_file)
-        return None
-
+        print(f"File content: {open(output_file, 'r').read()}")
+        raise
+    
     if "text" in transcription:
         result = transcription["text"]
     else:
         result = " ".join([chunk["text"] for chunk in transcription.get("chunks", [])])
-
-    cleanup_file(file_path)
-    cleanup_file(output_file)
-
+    
+    print("Transcription completed.")
+    
+    # Cleanup
+    cleanup_files(temp_audio, output_file)
+    
     return result
 
 @spaces.GPU(duration=60)
 def generate_summary_stream(transcription):
     print("Starting summary generation...")
+    print(f"Transcription length: {len(transcription)} characters")
+    
     detected_language = langdetect.detect(transcription)
     
     prompt = f"""Summarize the following video transcription in 150-300 words. 
@@ -130,35 +128,44 @@ def generate_summary_stream(transcription):
     
     response, history = model.chat(tokenizer, prompt, history=[])
     print(f"Final summary generated: {response[:100]}...")
+    print("Summary generation completed.")
     return response
 
 def process_youtube(url):
     if not url:
+        print("YouTube URL not provided.")
         return "Please enter a YouTube URL.", None
+    print(f"Processing YouTube URL: {url}")
+    
     try:
         audio_file = download_youtube_audio(url)
-        if audio_file is None:
-            return "Error downloading YouTube audio.", None
+        if not os.path.exists(audio_file):
+            raise FileNotFoundError(f"File {audio_file} does not exist after download.")
+        
+        print(f"Audio file found: {audio_file}")
+        print("Starting transcription...")
         transcription = transcribe_audio(audio_file)
-        if transcription is None:
-            return "Error transcribing audio.", None
+        print(f"Transcription completed. Length: {len(transcription)} characters")
         return transcription, None
     except Exception as e:
+        print(f"Error processing YouTube: {e}")
         return f"Processing error: {str(e)}", None
     finally:
-        if audio_file:
-            cleanup_file(audio_file)
+        cleanup_files(audio_file)
+        print(f"Directory content after processing: {os.listdir('.')}")
 
 def process_uploaded_video(video_path):
+    print(f"Processing uploaded video: {video_path}")
     try:
+        print("Starting transcription...")
         transcription = transcribe_audio(video_path)
-        if transcription is None:
-            return "Error transcribing video.", None
+        print(f"Transcription completed. Length: {len(transcription)} characters")
         return transcription, None
     except Exception as e:
+        print(f"Error processing video: {e}")
         return f"Processing error: {str(e)}", None
     finally:
-        cleanup_file(video_path)
+        cleanup_files(video_path)
 
 print("Setting up Gradio interface...")
 with gr.Blocks(theme=gr.themes.Soft()) as demo:
@@ -201,7 +208,9 @@ with gr.Blocks(theme=gr.themes.Soft()) as demo:
     def process_video_and_update(video):
         if video is None:
             return "No video uploaded.", "Please upload a video."
+        print(f"Video received: {video}")
         transcription, _ = process_uploaded_video(video)
+        print(f"Returned transcription: {transcription[:100] if transcription else 'No transcription generated'}...")
         return transcription or "Transcription error", ""
 
     video_button.click(process_video_and_update, inputs=[video_input], outputs=[transcription_output, summary_output])