v1

.gitignore

@@ -0,0 +1,2 @@
+# Ignore test notebooks
+*.ipynb

README.md

@@ -1,19 +1,17 @@
----
-title: Accentometer
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
----
+# 🎙️ English Accent Detector
 
-# Welcome to Streamlit!
+This project detects the English accent of speakers in video recordings using Whisper ASR and heuristic classification.
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+## 🔧 Features
+- Accepts MP4 or Loom video links
+- Extracts audio and transcribes with Whisper
+- Classifies accent (British, American, Australian)
+- Returns confidence score and transcript
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## 🚀 Hosted on Hugging Face Spaces
+Try it live: [Your HF Space Link](https://huggingface.co/spaces/your-username/accent-detector)
+
+## 🧪 Run Locally
+```bash
+pip install -r requirements.txt
+streamlit run src/streamlit_app.py

requirements.txt

@@ -1,3 +1,6 @@
 altair
-pandas
-streamlit
+streamlit
+moviepy
+transformers
+torch
+requests

src/detector.py

@@ -0,0 +1,17 @@
+from transformers import pipeline
+
+asr = pipeline("automatic-speech-recognition", model="openai/whisper-base")
+
+def detect_accent(audio_path: str):
+    result = asr(audio_path)
+    text = result["text"].lower()
+
+    # Heuristic accent classification (mocked rules)
+    if "cheers" in text or "mate" in text:
+        return "British", 85, text
+    elif "gonna" in text or "dude" in text:
+        return "American", 90, text
+    elif "bro" in text or "yeah nah" in text:
+        return "Australian", 80, text
+    else:
+        return "Uncertain", 50, text

src/downloader.py

@@ -0,0 +1,11 @@
+import requests
+
+def download_video(url: str, filename: str = "video.mp4") -> str:
+    response = requests.get(url, stream=True)
+    if response.status_code == 200:
+        with open(filename, "wb") as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+    else:
+        raise Exception("Failed to download video")
+    return filename

src/extractor.py

@@ -0,0 +1,6 @@
+from moviepy import VideoFileClip
+
+def extract_audio(video_path: str, output_path: str = "audio.wav") -> str:
+    video = VideoFileClip(video_path)
+    video.audio.write_audiofile(output_path, codec="pcm_s16le")
+    return output_path

src/streamlit_app.py

@@ -1,40 +1,29 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
+from downloader import download_video
+from extractor import extract_audio
+from detector import detect_accent
 
-"""
-# Welcome to Streamlit!
-
-Edit `/streamlit_app.py` to customize this app to your heart's desire :heart:.
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
-
-In the meantime, below is an example of what you can do with just a few lines of code:
-"""
-
-num_points = st.slider("Number of points in spiral", 1, 10000, 1100)
-num_turns = st.slider("Number of turns in spiral", 1, 300, 31)
-
-indices = np.linspace(0, 1, num_points)
-theta = 2 * np.pi * num_turns * indices
-radius = indices
-
-x = radius * np.cos(theta)
-y = radius * np.sin(theta)
-
-df = pd.DataFrame({
-    "x": x,
-    "y": y,
-    "idx": indices,
-    "rand": np.random.randn(num_points),
-})
-
-st.altair_chart(alt.Chart(df, height=700, width=700)
-    .mark_point(filled=True)
-    .encode(
-        x=alt.X("x", axis=None),
-        y=alt.Y("y", axis=None),
-        color=alt.Color("idx", legend=None, scale=alt.Scale()),
-        size=alt.Size("rand", legend=None, scale=alt.Scale(range=[1, 150])),
-    ))
+st.set_page_config(page_title="Accent Detector", page_icon="🎙️")
+
+st.title("🎙️ English Accent Classifier")
+st.write("Paste a public Loom or MP4 link and get an English accent classification.")
+
+video_url = st.text_input("Video URL (MP4 or Loom):")
+
+if st.button("Analyze") and video_url:
+    try:
+        with st.spinner("Downloading video..."):
+            video_file = download_video(video_url)
+
+        with st.spinner("Extracting audio..."):
+            audio_file = extract_audio(video_file)
+
+        with st.spinner("Transcribing & detecting accent..."):
+            accent, confidence, transcript = detect_accent(audio_file)
+
+        st.success(f"Accent: **{accent}**")
+        st.metric(label="Confidence", value=f"{confidence}%")
+        st.text_area("Transcript", transcript, height=150)
+
+    except Exception as e:
+        st.error(f"Error: {str(e)}")