Create app.py

app.py

@@ -0,0 +1,70 @@
+
+import os
+import uuid
+import torch
+import requests
+import gradio as gr
+from moviepy.editor import VideoFileClip
+from speechbrain.pretrained.interfaces import foreign_class
+
+# Load the pretrained model
+classifier = foreign_class(
+    source="Jzuluaga/accent-id-commonaccent_xlsr-en-english",
+    pymodule_file="custom_interface.py",
+    classname="CustomEncoderWav2vec2Classifier"
+)
+
+def extract_audio(video_path, output_wav="output.wav"):
+    video = VideoFileClip(video_path)
+    audio = video.audio
+    audio.write_audiofile(output_wav, codec='pcm_s16le', fps=16000)
+    return output_wav
+
+def download_video(url, filename="temp.mp4"):
+    response = requests.get(url, stream=True)
+    with open(filename, 'wb') as f:
+        for chunk in response.iter_content(chunk_size=8192):
+            f.write(chunk)
+    return filename
+
+def classify_video_accent(video_url):
+    uid = str(uuid.uuid4())
+    video_path = f"{uid}.mp4"
+    wav_path = f"{uid}.wav"
+
+    try:
+        download_video(video_url, video_path)
+        extract_audio(video_path, wav_path)
+
+        out_prob, score, index, text_lab = classifier.classify_file(wav_path)
+        confidence = torch.max(out_prob).item() * 100
+
+        return {
+            "accent": text_lab,
+            "confidence_score": f"{confidence:.2f}%",
+            "summary": f"The speaker is most likely using a(n) {text_lab} English accent."
+        }
+    finally:
+        for f in [video_path, wav_path]:
+            if os.path.exists(f):
+                os.remove(f)
+
+def gradio_accent_classifier(video_url):
+    try:
+        result = classify_video_accent(video_url)
+        return f"Accent: {result['accent']}
+Confidence: {result['confidence_score']}
+Summary: {result['summary']}"
+    except Exception as e:
+        return f"Error: {str(e)}"
+
+iface = gr.Interface(
+    fn=gradio_accent_classifier,
+    inputs=gr.Textbox(label="Public .mp4 Video URL"),
+    outputs="text",
+    title="English Accent Classifier",
+    description="Paste a direct link to a public .mp4 file to classify the English accent spoken in the video."
+)
+
+if __name__ == "__main__":
+    iface.launch()