metadata

title: Masked Word Predictor
emoji: 🌖
colorFrom: green
colorTo: indigo
sdk: gradio
sdk_version: 5.31.0
app_file: app.py
pinned: false
license: apache-2.0
short_description: Masked Word Predicto CPU

🔍 Masked Word Predictor

[]

🚀 Overview

Tap into Masked Language Modeling with DistilRoBERTa—no training required.
Type a sentence containing the special [MASK] token and get the model’s top-K completions instantly, all on free CPU.

Key AI concepts:
• Masked Language Modeling (MLM) • Transformer-based NLP • Distilled Architectures • Real-time Inference • Edge Deployment • Cloud-native Demo

✨ Features

🔑 Feature	🔍 Why It’s Cool
🧠 Transformer MLM	Uses DistilRoBERTa for lightning-fast fills
⚡ CPU-Only Inference	Runs on free-tier Space (2 vCPU / 16 GB RAM)
🔢 Top-K Control	Slider to choose how many predictions to show
🎨 Interactive UI	Gradio Blocks: input, button, and DataFrame
🔧 Zero-Config Deploy	Commit three files—Spaces auto-builds
💡 Educational Demos	Great for teaching how MLM works

🏗️ How It Works

User Input – Sentence with one or more [MASK] tokens.
MLM Pipeline – pipeline("fill-mask") computes token-level likelihoods.
Ranking – Returns the top-K predicted tokens with scores.
UI Rendering – Gradio shows each filled sentence and its confidence.

🛠️ Local Development

git clone https://github.com/your-username/masked-word-predictor.git
cd masked-word-predictor
python3 -m venv venv && source venv/bin/activate
pip install -r requirements.txt
python app.py