Named entity recognition, running on your own machine

bert-base-NER labels people, organisations, locations and miscellaneous entities with character offsets you can copy straight into a pipeline. The Piiranha model on the same page goes further and detects personal information — emails, phone numbers, account numbers, addresses — which is exactly the kind of text you should not be sending to a hosted API in the first place. Both run in the browser, so redaction happens before anything crosses the network.

named entity recognition onlinener tool freebert-base-ner demopii detection browserentity extraction toolredact pii locallytoken classification online

Frequently asked questions

Can I use this to redact documents before sending them elsewhere?

That is the intended use of the Piiranha model, and it is a sensible workflow because the detection runs locally. Always review the output — no NER model catches everything, especially unusual identifier formats.

Which entity types are supported?

bert-base-NER emits PER, ORG, LOC and MISC in CoNLL-2003 style. Piiranha covers a wider set of personal-data categories including emails, phone numbers and account identifiers.

Is my data uploaded to a server?

No. The model weights are downloaded from Hugging Face to your browser once, and every inference after that runs on your own GPU through WebGPU. Your text, images and audio are never sent anywhere — hjLabs.in has no inference server and no way to see your input.

Does this work on a phone?

Small models do. Recent mobile Chrome and Safari expose WebGPU, but memory is the binding limit — stay under roughly 200 MB of weights on Android, and expect iOS to reclaim the tab sooner. The catalog shows every download size up front so you can pick something that fits.

Can I use the output commercially?

That depends on the individual model, not on this site. Each model page links to its Hugging Face repository, where the licence is stated — most of the catalog is Apache-2.0 or MIT, a few are research-only. We add nothing on top: hjLabs.in claims no rights over anything you produce here.

Models available for this task

BERT Base NER — Xenova/bert-base-NER, 110 MB, 108M params
mBERT NER (10 languages) — Xenova/bert-base-multilingual-cased-ner-hrl, 182 MB, 177M params
DistilBERT NER (10 languages) — Xenova/distilbert-base-multilingual-cased-ner-hrl, 139 MB, 135M params
Piiranha v1 (PII) — onnx-community/piiranha-v1-detect-personal-information-ONNX, 334 MB, 280M params
BERT Small PII — onnx-community/bert-small-pii-detection-ONNX, 30 MB
DistilBERT NER — onnx-community/distilbert-NER-ONNX, 67 MB, 65M params
OpenMed PII Small 44M — YashaBor/OpenMed-PII-SuperClinical-Small-44M-v1-ONNX, 181 MB, 44M params
Biomedical NER (84 types) — onnx-community/biomedical-ner-all-ONNX, 68 MB, 65M params
Medical NER (41 types) — onnx-community/Medical-NER-ONNX, 231 MB, 184M params
Stanford De-identifier — onnx-community/stanford-deidentifier-base-ONNX, 111 MB, 108M params
OpenMed Disease NER — onnx-community/OpenMed-NER-DiseaseDetect-BioMed-335M-ONNX, 337 MB, 335M params
OpenMed PII Base 184M — onnx-community/OpenMed-PII-SuperClinical-Base-184M-v1-ONNX, 252 MB, 184M params
OpenMed Drug NER — onnx-community/OpenMed-NER-PharmaDetect-SuperMedical-125M-ONNX, 130 MB, 125M params
Italian Medical NER — onnx-community/italian_medical_ner-ONNX, 109 MB, 108M params

Explore the rest of the playground

Text & language models

LLM chat — Chat with a local LLM running on your own GPU
Text embeddings — Generate text embeddings locally, in the browser
Translation — Translate text offline with a local neural MT model
Summarization — Summarise long text with a model running on your machine
Sentiment analysis — Sentiment analysis that runs in your browser
Zero-shot text classification — Classify text into labels you make up on the spot
Question answering — Ask questions about a passage, get the exact answer span
Fill-mask — Watch a masked language model guess the missing word

Guides, comparisons & alternatives

Model catalog — The model catalog: what actually runs in a browser
WebGPU vs WASM — WebGPU vs WebAssembly for running models in a browser
Browser AI vs cloud API — Browser inference vs a hosted API: an honest comparison
Transformers.js vs WebLLM — Transformers.js vs WebLLM
Whisper model sizes — Choosing a Whisper size for browser transcription
fp32 vs q8 vs q4 — Picking a quantization level for browser inference
Why no image generation — Why this playground has no text-to-image generation
MedGemma in the browser — MedGemma in the browser: why it does not work, and what does
Free alternatives to paid AI tools — Free, local alternatives to paid AI services
remove.bg alternative — A remove.bg alternative that never uploads your image
Ollama alternative — An Ollama alternative that installs nothing
Open WebUI alternative — An Open WebUI alternative with no server behind it
Whisper API alternative — A Whisper API alternative that runs on your machine
Embeddings API alternative — An embeddings API alternative that costs nothing per token
FAQ — Frequently asked questions about browser-based AI
About — About this project

This playground needs JavaScript and WebGPU. Models are downloaded to your browser and executed on your own GPU, so there is nothing to show without a script engine. Enable JavaScript, or read the FAQ for what the site does.