Music Genre Classifier

 # utils/feature_extractor.py

import librosa

import numpy as np

def extract_features(file_path):

    y, sr = librosa.load(file_path, duration=30)

    mfccs = librosa.feature.mfcc(y=y, sr=sr, n_mfcc=40)

    mfccs_mean = np.mean(mfccs.T, axis=0)

    return mfccs_mean

from sklearn.ensemble import RandomForestClassifier

from sklearn.model_selection import train_test_split

import pandas as pd

import joblib

# Load features (extracted previously)

df = pd.read_csv("features_dataset.csv")  # Your dataset with MFCC + genre

X = df.drop('genre', axis=1)

y = df['genre']

X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)

clf = RandomForestClassifier()

clf.fit(X_train, y_train)

# Save model

joblib.dump(clf, "model/genre_model.pkl")

# app.py

import streamlit as st

import joblib

import numpy as np

from utils.feature_extractor import extract_features

import tempfile

# Load model

model = joblib.load("model/genre_model.pkl")

st.title("🎵 Music Genre Classifier")

st.write("Upload a music file to predict its genre")

uploaded_file = st.file_uploader("Choose a file", type=["mp3", "wav"])

if uploaded_file:

    # Save temporarily

    with tempfile.NamedTemporaryFile(delete=False) as tmp:

        tmp.write(uploaded_file.read())

        tmp_path = tmp.name

    # Extract features and predict

    features = extract_features(tmp_path)

    prediction = model.predict([features])[0]

    proba = model.predict_proba([features])

    st.success(f"Predicted Genre: **{prediction}**")

    st.bar_chart(proba[0])