Refactor README and implement accent detection functionality in Streamlit app

README.md

@@ -1,20 +1,12 @@
----
-title: Accent Detector
-emoji: 🚀
-colorFrom: red
-colorTo: red
-sdk: docker
-app_port: 8501
-tags:
-- streamlit
-pinned: false
-short_description: Streamlit template space
-license: mit
----
+# 🎤 Accent Detection Tool
 
-# Welcome to Streamlit!
+This app accepts a public video URL, extracts the audio, detects the English-speaking accent or language, and provides a confidence score.
 
-Edit `/src/streamlit_app.py` to customize this app to your heart's desire. :heart:
+## Usage
+- Enter a Loom or MP4 link.
+- Click "Analyze"
+- Get accent classification and score.
 
-If you have any questions, checkout our [documentation](https://docs.streamlit.io) and [community
-forums](https://discuss.streamlit.io).
+## Powered By
+- [SpeechBrain](https://huggingface.co/speechbrain/lang-id-commonlanguage_ecapa)
+- [Streamlit](https://streamlit.io)

requirements.txt

@@ -1,3 +1,6 @@
-altair
-pandas
-streamlit
+streamlit
+yt_dlp
+moviepy
+speechbrain
+torch
+torchaudio

src/streamlit_app.py

@@ -1,40 +1,44 @@
-import altair as alt
-import numpy as np
-import pandas as pd
 import streamlit as st
-
-"""
-# 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])),
-    ))
+import os
+import yt_dlp
+from moviepy.editor import VideoFileClip
+from speechbrain.pretrained import LanguageIdentification
+
+def download_video(url, video_path="video.mp4"):
+    ydl_opts = {"outtmpl": video_path}
+    with yt_dlp.YoutubeDL(ydl_opts) as ydl:
+        ydl.download([url])
+
+def extract_audio(video_path="video.mp4", audio_path="audio.wav"):
+    video = VideoFileClip(video_path)
+    video.audio.write_audiofile(audio_path)
+
+def detect_accent(audio_path="audio.wav"):
+    classifier = LanguageIdentification.from_hparams(source="speechbrain/lang-id-commonlanguage_ecapa", savedir="tmp_model")
+    prediction = classifier.classify_file(audio_path)
+    lang = prediction[1]
+    score = float(prediction[0][0])
+    return lang, score
+
+# --- Streamlit App ---
+st.title("🎤 Accent Detection Tool")
+url = st.text_input("Enter a public video URL (e.g. Loom or direct MP4)")
+
+if st.button("Analyze"):
+    try:
+        with st.spinner("Downloading video..."):
+            download_video(url)
+
+        with st.spinner("Extracting audio..."):
+            extract_audio()
+
+        with st.spinner("Detecting accent..."):
+            lang, confidence = detect_accent()
+
+        st.success("Analysis Complete!")
+        st.markdown(f"**Predicted Accent/Language:** `{lang}`")
+        st.markdown(f"**Confidence Score:** `{round(confidence * 100, 2)}%`")
+        st.caption("Note: This is based on SpeechBrain's language model and may group accents by broader language class.")
+
+    except Exception as e:
+        st.error(f"Error: {str(e)}")