| --- |
| title: Sentiment Analysis Demo |
| emoji: 🤗 |
| colorFrom: blue |
| colorTo: purple |
| sdk: static |
| pinned: false |
| license: mit |
| models: |
| - distilbert-base-uncased-finetuned-sst-2-english |
| --- |
| |
| # Sentiment Analysis Demo (in-browser) |
|
|
| A static, client-side sentiment analysis demo powered by |
| [🤗 Transformers.js](https://huggingface.co/docs/transformers.js). The model |
| ([`Xenova/distilbert-base-uncased-finetuned-sst-2-english`](https://huggingface.co/Xenova/distilbert-base-uncased-finetuned-sst-2-english), |
| an ONNX-converted version of |
| [`distilbert-base-uncased-finetuned-sst-2-english`](https://huggingface.co/distilbert-base-uncased-finetuned-sst-2-english)) |
| downloads and runs entirely in the visitor's browser via WebAssembly — no server, |
| no backend, no API calls, and no subscription required to host. |
|
|
| ## How it works |
|
|
| Open `index.html` — nothing to build or install. The page loads the model on |
| first visit (cached by the browser afterward), then classifies whatever text |
| you type as POSITIVE or NEGATIVE with a confidence score. |
|
|
| ## Running locally |
|
|
| Just open `index.html` directly in a browser, or serve the folder with any |
| static file server, e.g.: |
|
|
| ```bash |
| python -m http.server 8000 |
| ``` |
|
|
