Update app.py

app.py

@@ -2,11 +2,11 @@ import streamlit as st
 import os
 import tempfile
 import requests
-import subprocess
 import random
 import matplotlib.pyplot as plt
 import torchaudio
 import torch
+import ffmpeg
 
 # Load SpeechBrain
 try:
@@ -17,7 +17,7 @@ try:
     )
     SPEECHBRAIN_LOADED = True
 except Exception as e:
-    st.warning(f"Error loading SpeechBrain model: {e}. Running in simulation mode.")
+    st.warning(f"Could not load SpeechBrain model: {e}. Using simulation.")
     SPEECHBRAIN_LOADED = False
 
 class AccentAnalyzer:
@@ -69,16 +69,24 @@ class AccentAnalyzer:
     def analyze_accent(self, audio_path):
         if not SPEECHBRAIN_LOADED:
             return self._simulate_accent_classification(audio_path)
+
         try:
             signal, sr = torchaudio.load(audio_path)
-            if sr != 16000:
-                signal = torchaudio.transforms.Resample(sr, 16000)(signal)
+            duration = signal.shape[1] / sr
+            if duration < 1.0:
+                raise ValueError("Audio too short to analyze.")
+
             if signal.shape[0] > 1:
                 signal = signal.mean(dim=0, keepdim=True)
-            pred = speechbrain_classifier.classify_batch(signal.unsqueeze(0))
+            if sr != 16000:
+                signal = torchaudio.transforms.Resample(sr, 16000)(signal)
+            signal = signal.unsqueeze(0)  # [1, 1, time]
+
+            pred = speechbrain_classifier.classify_batch(signal)
             probs = pred[0].squeeze(0).tolist()
             labels = pred[1][0]
             scores = {speechbrain_classifier.hparams.label_encoder.ind2lab[i]: p * 100 for i, p in enumerate(probs)}
+
             if labels[0] == 'en':
                 result = self._simulate_accent_classification(audio_path)
                 result["all_scores"] = scores
@@ -93,50 +101,57 @@ class AccentAnalyzer:
             st.warning(f"Fallback to simulation: {e}")
             return self._simulate_accent_classification(audio_path)
 
-def download_and_extract_audio(url):
+def download_and_extract_audio(url_or_path, is_upload=False):
     temp_dir = tempfile.mkdtemp()
     video_path = os.path.join(temp_dir, "video.mp4")
     audio_path = os.path.join(temp_dir, "audio.wav")
 
-    if "youtube.com" in url or "youtu.be" in url:
-        from pytubefix import YouTube
-        yt = YouTube(url, use_po_token=True, client="WEB")
-        stream = yt.streams.filter(progressive=True, file_extension='mp4').first()
-        stream.download(output_path=temp_dir, filename="video.mp4")
+    if is_upload:
+        with open(video_path, "wb") as f:
+            f.write(url_or_path.read())
     else:
-        with requests.get(url, stream=True) as r:
+        with requests.get(url_or_path, stream=True) as r:
             r.raise_for_status()
             with open(video_path, 'wb') as f:
                 for chunk in r.iter_content(chunk_size=8192):
                     f.write(chunk)
 
-    subprocess.run([
-        "ffmpeg", "-i", video_path, "-ar", "16000", "-ac", "1", "-f", "wav", audio_path, "-y"
-    ], stdout=subprocess.DEVNULL, stderr=subprocess.DEVNULL)
-
+    (
+        ffmpeg
+        .input(video_path)
+        .output(audio_path, ar=16000, ac=1, format='wav')
+        .run(quiet=True, overwrite_output=True)
+    )
     return audio_path
 
-# Streamlit UI
-st.title("English Accent or Language Analyzer")
-url = st.text_input("Enter Public Video URL (YouTube or MP4)")
+# --- Streamlit App ---
+st.set_page_config(page_title="Accent Analyzer", layout="wide")
+st.title("🗣️ English Accent or Language Analyzer")
+
+st.markdown("Upload a video/audio file or provide a direct `.mp4` or `.wav` URL:")
+
+url = st.text_input("🔗 Enter Direct MP4/WAV URL:")
+uploaded_file = st.file_uploader("📁 Or upload a file (MP4/WAV)", type=["mp4", "wav"])
 
 if st.button("Analyze"):
-    if not url:
-        st.error("Please enter a URL.")
+    if not url and not uploaded_file:
+        st.error("Please enter a valid URL or upload a file.")
     else:
         try:
-            audio_path = download_and_extract_audio(url)
-            analyzer = AccentAnalyzer()
-            results = analyzer.analyze_accent(audio_path)
+            with st.spinner("Processing audio..."):
+                audio_path = download_and_extract_audio(uploaded_file if uploaded_file else url, is_upload=bool(uploaded_file))
+                analyzer = AccentAnalyzer()
+                results = analyzer.analyze_accent(audio_path)
 
-            st.markdown(results["explanation"])
+            st.success(results["explanation"])
 
             labels, values = zip(*results["all_scores"].items())
             fig, ax = plt.subplots()
-            ax.bar(labels, values)
+            ax.bar(labels, values, color='skyblue')
             ax.set_ylabel('Confidence (%)')
             ax.set_title('Accent/Language Confidence')
             plt.xticks(rotation=45)
             st.pyplot(fig)
+
         except Exception as e:
-            st.error(f"Error: {e}")
+            st.error(f"Failed to analyze: {e}")