Update app.py

app.py

@@ -8,89 +8,97 @@ import io
 import yt_dlp
 import PyPDF2
 
-# Define your OpenAI API key
-openai.api_key = "YOUR_OPENAI_API_KEY"
+# Define your OpenAI API key using environment variable (recommended for Hugging Face Spaces)
+openai.api_key = os.getenv("OPENAI_API_KEY")
 
 # Function to convert audio file to text using OpenAI's Whisper
-
 def transcribe_audio(audio_file):
-    # Load the audio file
-    audio = AudioSegment.from_file(audio_file)
-    # Export as WAV, which Whisper accepts
-    buffer = io.BytesIO()
-    audio.export(buffer, format="wav")
-    buffer.seek(0)
-
-    response = openai.Audio.transcribe(
-        "whisper-1",
-        file=buffer,
-        model='whisper',
-        response_format='verbose_json'
-    )
-    return response
+    try:
+        # Load the audio file
+        audio = AudioSegment.from_file(audio_file)
+        # Export as WAV, which Whisper accepts
+        buffer = io.BytesIO()
+        audio.export(buffer, format="wav")
+        buffer.seek(0)
+
+        response = openai.Audio.transcribe(
+            "whisper-1",
+            file=buffer,
+            model='whisper',
+            response_format='verbose_json'
+        )
+        return response
+    except Exception as e:
+        print(f"Error in transcribe_audio: {str(e)}")
+        raise
 
 # Function to download audio from YouTube URL
-
 def download_youtube_audio(url):
-    ydl_opts = {
-        'format': 'bestaudio/best',
-        'outtmpl': 'downloaded_audio.%(ext)s',
-        'postprocessors': [{
-            'key': 'FFmpegExtractAudio',
-            'preferredcodec': 'mp3',
-            'preferredquality': '192',
-        }],
-    }
-    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
-        ydl.download([url])
-    return 'downloaded_audio.mp3'
+    try:
+        ydl_opts = {
+            'format': 'bestaudio/best',
+            'outtmpl': 'downloaded_audio.%(ext)s',
+            'postprocessors': [{
+                'key': 'FFmpegExtractAudio',
+                'preferredcodec': 'mp3',
+                'preferredquality': '192',
+            }],
+        }
+        with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+            ydl.download([url])
+        return 'downloaded_audio.mp3'
+    except Exception as e:
+        print(f"Error in download_youtube_audio: {str(e)}")
+        raise
 
 # Function to extract text from PDF
-
 def extract_text_from_pdf(pdf_file):
-    pdf_reader = PyPDF2.PdfFileReader(pdf_file)
-    text = ""
-    for page_num in range(pdf_reader.numPages):
-        text += pdf_reader.getPage(page_num).extract_text() + "\n"
-    return text
+    try:
+        pdf_reader = PyPDF2.PdfFileReader(pdf_file)
+        text = ""
+        for page_num in range(pdf_reader.numPages):
+            text += pdf_reader.getPage(page_num).extract_text() + "\n"
+        return text
+    except Exception as e:
+        print(f"Error in extract_text_from_pdf: {str(e)}")
+        raise
 
 # Function to generate summarised lecture notes using GPT-3.5
-
 def generate_summary(transcription):
-    transcription_text = "\n".join([f"{segment['start']:.2f}-{segment['end']:.2f}: {segment['text']}" for segment in transcription['segments']])
-    prompt = f"""
-    You are an intelligent assistant that will summarize the transcription below.
-    The transcription text is:
-    {transcription_text}
-
-    Summarize the content into 1000 tokens or less, focusing on the key topics and main points.
-    """
-    response = openai.ChatCompletion.create(
-        model="gpt-3.5-turbo",
-        messages=[
-            {"role": "system", "content": "You are an expert summarizer."},
-            {"role": "user", "content": prompt}
-        ]
-    )
-    summary = response['choices'][0]['message']['content']
-    return summary
+    try:
+        transcription_text = "\n".join([f"{segment['start']:.2f}-{segment['end']:.2f}: {segment['text']}" for segment in transcription['segments']])
+        prompt = f"""
+        You are an intelligent assistant that will summarize the transcription below.
+        The transcription text is:
+        {transcription_text}
+
+        Summarize the content into 1000 tokens or less, focusing on the key topics and main points.
+        """
+        response = openai.ChatCompletion.create(
+            model="gpt-3.5-turbo",
+            messages=[
+                {"role": "system", "content": "You are an expert summarizer."},
+                {"role": "user", "content": prompt}
+            ]
+        )
+        summary = response['choices'][0]['message']['content']
+        return summary
+    except Exception as e:
+        print(f"Error in generate_summary: {str(e)}")
+        raise
 
 # Define the main function to handle transcription and summary generation
-
 def process_lecture(input_type, audio_input, pdf_input, youtube_input, lesson_plan):
     transcription = ""
     try:
-        if input_type == "Audio File":
-            if audio_input is not None:
-                transcription = transcribe_audio(audio_input)
-        elif input_type == "YouTube URL":
-            if youtube_input:
-                audio_path = download_youtube_audio(youtube_input)
-                with open(audio_path, "rb") as f:
-                    transcription = transcribe_audio(f)
-        elif input_type == "PDF Document":
-            if pdf_input is not None:
-                transcription = extract_text_from_pdf(pdf_input)
+        if input_type == "Audio File" and audio_input is not None:
+            transcription = transcribe_audio(audio_input)
+        elif input_type == "YouTube URL" and youtube_input:
+            audio_path = download_youtube_audio(youtube_input)
+            with open(audio_path, "rb") as f:
+                transcription = transcribe_audio(f)
+        elif input_type == "PDF Document" and pdf_input is not None:
+            transcription = extract_text_from_pdf(pdf_input)
     except Exception as e:
         return f"Error during processing: {str(e)}", "No summary available."
     
@@ -100,7 +108,7 @@ def process_lecture(input_type, audio_input, pdf_input, youtube_input, lesson_pl
             summary = generate_summary(transcription)
             return transcription_text, summary
         except Exception as e:
-            return "Transcription generated, but error during summary generation: {str(e)}", "No summary available."
+            return f"Transcription generated, but error during summary generation: {str(e)}", "No summary available."
     else:
         return "No transcription available.", "No summary available."
 
@@ -129,4 +137,5 @@ with gr.Blocks() as demo:
     submit_btn.click(fn=process_lecture, inputs=[input_type, audio_input, pdf_input, youtube_input, lesson_plan_input], outputs=[transcription_output, summary_output])
 
 # Launch the interface
-demo.launch(share=True)
+if __name__ == "__main__":
+    demo.launch(share=True)