Spaces:
Running
Running
| 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 | |
| [](https://huggingface.co/spaces/ghostai1/Masked-Word-Predictor) | |
| [] | |
| [](https://huggingface.co/distilroberta-base) | |
| [](LICENSE) | |
| --- | |
| ## 🚀 Live Demo | |
| Try it out here: | |
| 🔗 **https://huggingface.co/spaces/ghostai1/Masked-Word-Predictor** | |
| --- | |
| ## 📝 What It Does | |
| The **Masked Word Predictor** uses a pre-trained DistilRoBERTa model to perform **masked language modeling** in real time—100 % CPU, zero infra. | |
| Type any sentence containing the special token `[MASK]` and get the model’s **top-K** fill-in predictions, complete with confidence scores. | |
| > Example use case: | |
| > > Input: | |
| > > “The new conditioner made my hair feel [MASK].” | |
| > > | |
| > > Output: | |
| > > | sequence | score | | |
| > > |--------------------------------------------|--------| | |
| > > | “The new conditioner made my hair feel soft.” | 0.987 | | |
| > > | “The new conditioner made my hair feel smooth.” | 0.923 | | |
| > > … | |
| --- | |
| ## ✨ Key Features | |
| | 🔑 Feature | 🔍 Description | | |
| |--------------------------|------------------------------------------------------------------| | |
| | **🧠 Transformer MLM** | DistilRoBERTa fill-mask pipeline for lightning-fast predictions | | |
| | **⚙️ Top-K Control** | Slider to choose how many completions you’d like (1–10) | | |
| | **💻 CPU-Only Inference** | Runs on free 2 vCPU/16 GB RAM Spaces—no GPU needed | | |
| | **🎨 Interactive UI** | Gradio Blocks with clear input, button, and results table | | |
| | **🔧 Zero-Config Deploy** | Drop in three files; Spaces auto-builds & hosts your demo | | |
| --- | |
| ## 🔨 How to Use | |
| 1. **Open the demo** at | |
| `https://huggingface.co/spaces/ghostai1/Masked-Word-Predictor` | |
| 2. In the **Input Sentence** field, type a sentence with exactly one `[MASK]` token. | |
| - Example: `“She bought a new [MASK] at the salon.”` | |
| 3. Set **Top K Predictions** via the slider (default = 5). | |
| 4. Click **Predict 🏷️**. | |
| 5. View the **Predictions** table: each row shows the completed sentence and its confidence. | |
| --- | |
| ## 🛠️ Local Development | |
| ```bash | |
| git clone https://github.com/ghostai1/Masked-Word-Predictor.git | |
| cd Masked-Word-Predictor | |
| python3 -m venv venv && source venv/bin/activate | |
| pip install -r requirements.txt | |
| python app.py | |
| ## Latest Update | |
| - Updated Gradio UI to version 5.31.0 for enhanced performance. 🔍 - May 29, 2025 📝 | |
| - Added support for multiple [MASK] tokens. - June 10, 2025 📝 | |
| - Improved DistilRoBERTa prediction speed. 🌖 - June 09, 2025 📝 | |
| - Updated Gradio UI to version 5.31.0 for enhanced performance. 🌖 - June 08, 2025 📝 | |
| - Optimized CPU inference for larger inputs. 🔍 - June 07, 2025 📝 | |
| - Enhanced top-K slider functionality. ⚙️ - June 06, 2025 📝 | |
| - Added support for multiple [MASK] tokens. 🚀 - June 05, 2025 📝 | |
| - Improved DistilRoBERTa prediction speed. 🧠 - June 04, 2025 📝 | |
| - Updated Gradio UI to version 5.31.0 for enhanced performance. 🚀 - June 03, 2025 📝 | |
| - Optimized CPU inference for larger inputs. 🧠 - June 02, 2025 📝 | |
| - Enhanced top-K slider functionality. - June 01, 2025 📝 | |
| - Added support for multiple [MASK] tokens. 🌖 - May 31, 2025 📝 | |
| - Improved DistilRoBERTa prediction speed. ⚙️ - May 30, 2025 📝 | |
| **Website**: https://ghostainews.com/ | |
| **Discord**: https://discord.gg/BfA23aYz |