Audio CNN

HI THIS IS PUJIT SWIKRIT!!

Overview

Unlock the power of audio intelligence with our advanced Deep Convolutional Neural Network for sound classification. Built with a ResNet-style architecture and tailored for high-performance inference, this project transforms raw audio into actionable insights using Mel Spectrograms, innovative data augmentation, and real-time visualization.

Features:

• 🧠 Deep Audio CNN for sound classification
• 🧱 ResNet-style architecture with residual blocks
• 🎼 Mel Spectrogram audio-to-image conversion
• 🎛️ Data augmentation with Mixup & Time/Frequency Masking
• ⚡ Serverless GPU inference with Modal
• 📊 Interactive Next.js & React dashboard
• 👁️ Visualization of internal CNN feature maps
• 📈 Real-time audio classification with confidence scores
• 🌊 Waveform and Spectrogram visualization
• 🚀 FastAPI inference endpoint
• ⚙️ Optimized training with AdamW & OneCycleLR scheduler
• 📈 TensorBoard integration for training analysis
• 🛡️ Batch Normalization for stable & fast training
• 🎨 Modern UI with Tailwind CSS & Shadcn UI
• ✅ Pydantic data validation for robust API requests

Setup

Follow these steps to install and set up the project.

Clone the Repository

git clone https://github.com/codecreed20/cnn-audio.git

Install Python

Download and install Python if not already installed. Use the link below for guidance on installation: Python Download

Create a virtual environment with Python 3.12.

Backend

Navigate to folder:

cd audio-cnn

Install dependencies:

pip install -r requirements.txt

Modal setup:

modal setup

Run on Modal:

modal run main.py

Deploy backend:

modal deploy main.py

Frontend

Install dependencies:

cd audio-cnn-visualisation
npm i

Run:

npm run dev