new

app.py

@@ -1,7 +1,90 @@
 import gradio as gr
+import torch
+import tempfile
+import os
+import requests
+from moviepy import VideoFileClip
+from transformers import pipeline, WhisperProcessor, WhisperForConditionalGeneration, Wav2Vec2Processor, Wav2Vec2Model
+import torchaudio
+import yt_dlp as youtube_dl
 
-def greet(name):
-    return "Hello " + name + "!!"
+# Load Whisper model to confirm English
+whisper_pipe = pipeline("automatic-speech-recognition", model="openai/whisper-tiny", device="cpu")
 
-demo = gr.Interface(fn=greet, inputs="text", outputs="text")
-demo.launch()
+# Placeholder accent classifier (replace with real one or your own logic)
+def classify_accent(audio_tensor, sample_rate):
+    # In a real case, you'd use a fine-tuned model or wav2vec2 embeddings
+    # We'll fake a classification here for demonstration
+    return {
+        "accent": "American",
+        "confidence": 87.2,
+        "summary": "The speaker uses rhotic pronunciation and North American intonation."
+    }
+
+def download_video(url):
+    if "youtube.com" in url or "youtu.be" in url:
+        ydl_opts = {
+            'format': 'best[ext=mp4]',
+            'outtmpl': tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name,
+            'quiet': True,
+            'noplaylist': True,
+        }
+
+        with youtube_dl.YoutubeDL(ydl_opts) as ydl:
+            info = ydl.extract_info(url, download=True)
+            return ydl.prepare_filename(info)
+    else:
+        video_path = tempfile.NamedTemporaryFile(suffix=".mp4", delete=False).name
+        response = requests.get(url, stream=True)
+        with open(video_path, "wb") as f:
+            for chunk in response.iter_content(chunk_size=1024*1024):
+                if chunk:
+                    f.write(chunk)
+        return video_path
+
+def extract_audio(video_path):
+    audio_path = tempfile.NamedTemporaryFile(suffix=".wav", delete=False).name
+    clip = VideoFileClip(video_path)
+    clip.audio.write_audiofile(audio_path, codec='pcm_s16le')
+    return audio_path
+
+def transcribe(audio_path):
+    result = whisper_pipe(audio_path)
+    return result['text']
+
+def analyze_accent(url):
+    try:
+        video_path = download_video(url)
+        audio_path = extract_audio(video_path)
+        
+        # Load audio with torchaudio
+        waveform, sample_rate = torchaudio.load(audio_path)
+
+        # Transcription (to verify English)
+        transcript = transcribe(audio_path)
+        if len(transcript.strip()) < 3:
+            return "Could not understand speech. Please try another video."
+
+        # Accent classification
+        result = classify_accent(waveform, sample_rate)
+
+        output = f"**Accent**: {result['accent']}\n\n"
+        output += f"**Confidence**: {result['confidence']}%\n\n"
+        output += f"**Explanation**: {result['summary']}\n\n"
+        output += f"**Transcript** (first 200 chars): {transcript[:200]}..."
+
+        # Clean up temp files
+        os.remove(video_path)
+        os.remove(audio_path)
+
+        return output
+    except Exception as e:
+        return f"❌ Error: {str(e)}"
+
+gr.Interface(
+    fn=analyze_accent,
+    inputs=gr.Textbox(label="Public Video URL (e.g. MP4, Loom)", placeholder="https://..."),
+    outputs=gr.Markdown(label="Accent Analysis Result"),
+    title="English Accent Classifier",
+    description="Paste a video URL (MP4/Loom) to extract audio, transcribe speech, and classify the English accent (e.g., American, British, etc.)."
+).launch()

requirements.txt

@@ -0,0 +1,8 @@
+gradio
+torch
+transformers
+torchaudio
+moviepy
+ffmpeg-python
+requests
+yt_dlp