AI/ML Playground – Multi-Task Machine Learning Demo Suite for NLP, Vision, and Speech

AI/ML Playground – Multi-Task Machine Learning Demo Suite (NLP + Vision + Speech)

AI/ML Playground is a consolidated collection of hands-on machine learning mini-projects that I built to explore and demonstrate a wide range of AI capabilities across Natural Language Processing, Computer Vision, and Speech.

Instead of building isolated scripts, I structured this as a single “playground” repository where each module focuses on one real-world AI task — from text generation and summarization to object detection, image segmentation, and speech recognition. The project helped me build strong practical intuition around model inputs/outputs, preprocessing pipelines, and how different AI tasks can be packaged into reusable, testable components.

Key Modules / Capabilities

NLP (Text)

• Text Classification – categorize input text into labels
• Text Generation – generate coherent text from prompts
• Summarization – shorten long passages into concise summaries
• Document Question Answering – answer questions based on document content

Computer Vision (Images)

• Image Classification – identify what’s in an image
• Image Segmentation – pixel-level separation of objects/regions
• Object Detection – bounding-box detection of objects
• Image Captioning – generate human-like descriptions for images
• Visual Question Answering (VQA) – answer questions about an image

Speech & Audio

• GTTS Text-to-Speech – convert text into speech output
• Automatic Speech Recognition (ASR) – convert speech to text
• Audio Classification – classify audio types/events

Example: Text-to-Speech (GTTS)

from gtts import gTTS

tts = gTTS("Hello from the AI/ML Playground!", lang="en")
tts.save("output.mp3")