deepanwadhwa / zink
A Python package for zero-shot text anonymization using Transformer-based NER models.
Why this job: matched by what the repo talks about: text, model, shot, bas
What it does
- 1. Replacing Entities
- 2. Custom Replacements (Bring Your Own Data)
- 3. Shielding LLM and API Calls
- 4. Persistent Entity Mapping
Get started
uv add "zink[cpu]"
# or
pip install "zink[cpu]"- Maintenance
- Active
- Last commit 33 days ago
- Stars
- 112
- On GitHub
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.6.3
- Released 11 months ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- Not stated
- Last 90 days
- Issues
- 100% closed
- 0 still open
- Pull requests
- 13 merged
- 0 waiting
- Releases
- 4
- 1 in the last year
- Contributing guide (opens in new tab)
- No security policy
- Code of conduct (opens in new tab)
More: languages, topics and project record
Languages
- Python 100%
- Dockerfile <1%
Topics
- ai
- anonymization
- hippaa
- machine-learning
- nlp
- privacy
Project record
- JobSpeech and audio
- StatusListed
- Commits89
- Forks2
- Watching1
- Stars in 28 days0
- CreatedMar 4, 2025
- First seen by usNov 7, 2026
- CheckedNov 8, 2026