metadata

title: Accent Classifier
emoji: 🚀
colorFrom: red
colorTo: red
sdk: docker
app_port: 8501
tags:
  - streamlit
pinned: false
short_description: Streamlit template space

English Accent Detector (SpeechBrain)

This Streamlit app detects English accents from speech in public video URLs using the SpeechBrain accent classification model.

Features

Input a public video URL (MP4, Loom, etc.)
Downloads the video
Extracts up to 60 seconds of audio
Classifies English accent with confidence score
Provides an explanation of the detected accent

Requirements

Python 3.12 or higher
ffmpeg installed and available in PATH (required by moviepy)
Internet connection (to download videos and model weights)

Setup

Clone the repo (or copy your project files):

git clone https://github.com/Kedar43/accent_detector.git
cd accent_detector

Create and activate a virtual environment (optional but recommended):

python -m venv venv
source venv/bin/activate   # On Windows: venv\Scripts\activate

Install dependencies:
```
pip install -r requirements.txt
```

Usage

Run the Streamlit app:

streamlit run app.py

This will open a browser window/tab with the app interface.
Paste a public video URL (must be MP4).
Wait while the app downloads the video and processes audio (up to 60 seconds).
View the detected English accent, confidence score, and explanation.

Testing the app

Use sample public MP4 videos containing English speech with distinct accents.
The app logs runtime info and errors to app.log in the working directory.
If errors occur, check app.log for detailed traceback and messages.

Notes

The SpeechBrain model is loaded once and cached to improve performance on repeated runs.
Temporary video and audio files are deleted automatically after processing.
Accuracy depends on the quality of audio and the SpeechBrain model’s training data.
Make sure video URLs are publicly accessible without authentication.