PopularMajor Project
Machine Learning
AI Resume Screening System
NLP pipeline that ranks candidates against a job description
- Python
- spaCy
- scikit-learn
- FastAPI
- +2
₹4,499₹7,999
4.9/214 reviews
Machine Learning · Major Project
Music Genre Classification
Classifies song clips by genre from MFCCs and spectrograms
2-3 weeks build
Overview
Classifies thirty-second music clips into ten genres using the public GTZAN dataset. Audio is cut into short segments, MFCCs and mel-spectrograms are extracted with Librosa, and a CNN is trained alongside a feature-based random forest baseline. Splits are made by track, not segment, so pieces of the same song never appear in both training and test data.
What makes it stand up
- 01MFCC and mel-spectrogram feature extraction pipeline
- 02Track-level splits to prevent segment leakage
- 03CNN compared with a random forest on summary features
- 04Confusion matrix and per-genre F1 in the report
- 05Upload a clip and see genre probabilities in the demo
Module breakdown
- 01
Audio prep
Resampling, segmenting and normalising clips.
- 02
Features
MFCC, chroma and mel-spectrogram extraction.
- 03
Baseline
Random forest on aggregated audio features.
- 04
CNN
Convolutional model trained on spectrogram segments.
- 05
Demo
Streamlit upload with per-genre probability bars.
After this, you will be able to
- Explain what a mel-spectrogram represents
- Defend track-level splitting against data leakage
- Demo classifying a clip the examiner provides
Technology stack
- Python
- TensorFlow
- Librosa
- scikit-learn
- Streamlit
- Level
- Major Project
- Domain
- Machine Learning
- Build time
- 2-3 weeks
- Difficulty
You receive
- Complete, commented source code
- 60-90 page project report (IEEE format)
- Editable presentation deck
- Architecture, ER and UML diagrams
- Local setup and deployment guide
- Sample dataset or seed data
- Viva question bank with answers
- One 45-minute walkthrough call
- 30 days of doubt-clearing support