Enhance Dockerfile for improved network reliability and add cookies directory; update Streamlit app for better YouTube authentication handling and user guidance

Dockerfile

@@ -19,6 +19,7 @@ RUN apt-get update --allow-releaseinfo-change || (sleep 2 && apt-get update) &&
 # Set pip to have more retries and timeout
 ENV PIP_DEFAULT_TIMEOUT=100
 ENV PIP_RETRIES=3
+ENV PYTHONUNBUFFERED=1
 
 # Copy requirements and install Python dependencies
 COPY requirements.txt ./
@@ -26,6 +27,9 @@ RUN pip install --upgrade pip && \
     pip install --no-cache-dir -r requirements.txt || \
     (sleep 2 && pip install --no-cache-dir -r requirements.txt)
 
+# Create cookies directory for user uploads
+RUN mkdir -p /app/cookies
+
 # Copy source code
 COPY src/ ./src/
 

src/streamlit_app.py

@@ -56,23 +56,40 @@ def download_video(url, video_path="video.mp4", cookies_file=None):
     """Download a video from a URL"""
     ydl_opts = {
         "outtmpl": video_path,
+        "quiet": False,
+        "no_warnings": False,
+        "verbose": True  # More detailed output for debugging
     }
     
-    # Try to use provided cookies file first if it exists
+    # Only use cookies if explicitly provided via file upload
+    # Don't try to access browser cookies in Docker container
     if cookies_file and os.path.exists(cookies_file):
         ydl_opts["cookiefile"] = cookies_file
-    else:
-        # Fall back to browser cookies
-        ydl_opts["cookiesfrombrowser"] = ("chrome",)
     
     try:
+        # Special handling for YouTube URLs to try without cookies first
+        is_youtube = "youtube" in url.lower() or "youtu.be" in url.lower()
+        
         with yt_dlp.YoutubeDL(ydl_opts) as ydl:
             ydl.download([url])
-        return os.path.exists(video_path)
+            
+        if os.path.exists(video_path):
+            return True
+        else:
+            st.error(f"Video downloaded but file not found: {video_path}")
+            return False
     except Exception as e:
-        st.error(f"Download error: {str(e)}")
-        if "youtube" in url.lower() and "bot" in str(e).lower():
-            st.warning("YouTube is requesting authentication. Please see the 'Having trouble with YouTube videos?' section for help.")
+        error_msg = str(e)
+        st.error(f"Download error: {error_msg}")
+        
+        # Provide specific guidance based on error type
+        if is_youtube and ("bot" in error_msg.lower() or "sign in" in error_msg.lower()):
+            st.warning("YouTube requires authentication. Please upload a cookies.txt file or try a direct video link.")
+        elif "not find" in error_msg.lower() and "cookies" in error_msg.lower():
+            st.warning("Browser cookies could not be accessed. Please upload a cookies.txt file.")
+        elif "network" in error_msg.lower() or "timeout" in error_msg.lower():
+            st.warning("Network error. Please check your internet connection and try again.")
+            
         return False
 
 def extract_audio(video_path="video.mp4", audio_path="audio.wav"):
@@ -271,6 +288,20 @@ st.set_page_config(
 
 st.title("🎤 English Accent Detection Tool")
 st.markdown("""
+This application analyzes a speaker's English accent from video URLs or audio uploads, 
+providing detailed insights for hiring evaluation purposes.
+""")
+
+# Add container for tips
+with st.container():
+    st.info("""
+    💡 **Tips for best results:**
+    - Use **Loom** or **Vimeo** videos (more reliable than YouTube)
+    - For YouTube videos, you may need to provide cookies
+    - Audio clips of 15-30 seconds work best
+    - Clear speech with minimal background noise is ideal
+    """)
+st.markdown("""
 This app analyzes a speaker's English accent from a video or audio source.
 It provides:
 - Classification of the accent (British, American, etc.)
@@ -282,31 +313,47 @@ It provides:
 tab1, tab2 = st.tabs(["Video URL", "Upload Audio"])
 
 with tab1:
-    url = st.text_input("Enter a public video URL (e.g. Loom, YouTube, or direct MP4 link)")
+    st.markdown("### 🎬 Analyze video from URL")
+    url = st.text_input("Enter a public video URL", 
+                       placeholder="https://www.loom.com/..., https://vimeo.com/..., or direct MP4 link")
+    
+    # Recommend alternative sources
+    st.caption("⚠️ **Note**: YouTube videos often require authentication. For best results, use Loom, Vimeo or direct video links.")
     
     # Add file uploader for cookies.txt
     cookies_file = None
-    uploaded_cookies = st.file_uploader("Optional: Upload cookies.txt for YouTube authentication", type="txt", help="Only needed if you have issues with YouTube videos")
+    uploaded_cookies = st.file_uploader("Upload cookies.txt file for YouTube (if needed)", 
+                                      type="txt", 
+                                      help="Only needed for YouTube videos that require authentication")
     
     if uploaded_cookies is not None:
         # Save the uploaded cookies file to a temporary file
         cookies_file = f"cookies_{int(time.time())}.txt"
         with open(cookies_file, "wb") as f:
             f.write(uploaded_cookies.getbuffer())
+        st.success("Cookies file uploaded successfully!")
     
     with st.expander("Having trouble with YouTube videos?"):
         st.markdown("""
-        **YouTube Authentication Issues**
+        ### YouTube Authentication Issues
+        
+        YouTube's anti-bot measures often block automated video downloads. To solve this:
         
-        YouTube sometimes requires authentication to verify you're not a bot. If you encounter errors while analyzing YouTube videos, try these solutions:
+        #### Option 1: Use Alternative Video Sources (Recommended)
+        These typically work without authentication issues:
+        - [Loom](https://www.loom.com/) - Great for screen recordings
+        - [Vimeo](https://vimeo.com/) - High-quality video hosting
+        - [Streamable](https://streamable.com/) - Simple video sharing
+        - Any direct MP4 link
         
-        1. **Use a different video source**: Try Loom or a direct MP4 link instead
-        2. **Export cookies from your browser**:
-           - Install the [cookies.txt extension](https://chrome.google.com/webstore/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc) for Chrome
-           - Visit YouTube and login 
-           - Use the extension to export your cookies to a file
-           - Place the cookies file in the app's directory
-        3. **Try a shorter video**: YouTube may be less likely to require authentication for shorter clips
+        #### Option 2: Upload Cookies for YouTube
+        1. Install a browser extension like [Get cookies.txt](https://chrome.google.com/webstore/detail/get-cookiestxt-locally/cclelndahbckbenkjhflpdbgdldlbecc)
+        2. Login to YouTube in your browser
+        3. Use the extension to export cookies to a .txt file
+        4. Upload the cookies.txt file using the uploader above
+        
+        #### Option 3: Use Audio Upload Instead
+        The 'Upload Audio' tab allows direct analysis of audio files without URL issues.
         """)
     
     if st.button("Analyze Video"):
@@ -374,13 +421,27 @@ with tab1:
                 st.error(f"Error during analysis: {str(e)}")
 
 with tab2:
-    uploaded_file = st.file_uploader("Upload an audio file (WAV, MP3, etc.)", type=["wav", "mp3", "m4a", "ogg"])
+    st.markdown("### 🎵 Upload Audio File")
+    st.caption("**Recommended option!** Direct audio upload is more reliable than video URLs.")
+    
+    uploaded_file = st.file_uploader("Upload an audio file", 
+                                   type=["wav", "mp3", "m4a", "ogg", "flac"], 
+                                   help="Support for WAV, MP3, M4A, OGG and FLAC formats")
     
     if uploaded_file is not None:
+        # Show a preview of the audio
+        st.markdown("#### Audio Preview:")
         st.audio(uploaded_file)
         
-        if st.button("Analyze Audio"):
-            with st.spinner("Analyzing audio... (this may take a moment)"):
+        st.markdown("#### Ready for Analysis")
+        col1, col2 = st.columns([1, 3])
+        with col1:
+            analyze_button = st.button("Analyze Audio", type="primary", use_container_width=True)
+        with col2:
+            st.caption("Tip: 15-30 seconds of clear speech works best for accent detection")
+        
+        if analyze_button:
+            with st.spinner("Analyzing audio... (this may take 15-30 seconds)"):
                 try:
                     results = process_uploaded_audio(uploaded_file)