Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/humansignal/label-studio-transformers
Label data using HuggingFace's transformers and automatically get a prediction service
https://github.com/humansignal/label-studio-transformers
bert data-labeling label-studio natural-language-processing natural-language-understanding nlp pytorch-transformers text-labeling transformers
Last synced: about 17 hours ago
JSON representation
Label data using HuggingFace's transformers and automatically get a prediction service
- Host: GitHub
- URL: https://github.com/humansignal/label-studio-transformers
- Owner: HumanSignal
- License: apache-2.0
- Created: 2019-12-11T14:29:02.000Z (almost 5 years ago)
- Default Branch: master
- Last Pushed: 2023-06-20T21:41:20.000Z (over 1 year ago)
- Last Synced: 2024-11-08T07:03:26.079Z (6 days ago)
- Topics: bert, data-labeling, label-studio, natural-language-processing, natural-language-understanding, nlp, pytorch-transformers, text-labeling, transformers
- Language: Python
- Homepage: https://labelstud.io/
- Size: 190 KB
- Stars: 177
- Watchers: 9
- Forks: 30
- Open Issues: 7
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Label Studio for Hugging Face's Transformers
[Website](https://labelstud.io/) • [Docs](https://labelstud.io/guide) • [Twitter](https://twitter.com/heartexlabs) • [Join Slack Community 
](https://slack.labelstud.io/?source=github-1)
**Transfer learning for NLP models by annotating your textual data without any additional coding.**
This package provides a ready-to-use container that links together:
- [Label Studio](https://github.com/heartexlabs/label-studio) as annotation frontend
- [Hugging Face's transformers](https://github.com/huggingface/transformers) as machine learning backend for NLP
[
](https://github.com/heartexlabs/label-studio-transformers)
### Quick Usage
#### Install Label Studio and other dependencies
```bash
pip install -r requirements.txt
```
##### Create ML backend with BERT classifier
```bash
label-studio-ml init my-ml-backend --script models/bert_classifier.py
cp models/utils.py my-ml-backend/utils.py
# Start ML backend at http://localhost:9090
label-studio-ml start my-ml-backend
# Start Label Studio in the new terminal with the same python environment
label-studio start
```
1. Create a project with `Choices` and `Text` tags in the labeling config.
2. Connect the ML backend in the Project settings with `http://localhost:9090`
##### Create ML backend with BERT named entity recognizer
```bash
label-studio-ml init my-ml-backend --script models/ner.py
cp models/utils.py my-ml-backend/utils.py
# Start ML backend at http://localhost:9090
label-studio-ml start my-ml-backend
# Start Label Studio in the new terminal with the same python environment
label-studio start
```
1. Create a project with `Labels` and `Text` tags in the labeling config.
2. Connect the ML backend in the Project settings with `http://localhost:9090`
#### Training and inference
The browser opens at `http://localhost:8080`. Upload your data on **Import** page then annotate by selecting **Labeling** page.
Once you've annotate sufficient amount of data, go to **Model** page and press **Start Training** button. Once training is finished, model automatically starts serving for inference from Label Studio, and you'll find all model checkpoints inside `my-ml-backend//` directory.
[Click here](https://labelstud.io/guide/ml.html) to read more about how to use Machine Learning backend and build Human-in-the-Loop pipelines with Label Studio
## License
This software is licensed under the [Apache 2.0 LICENSE](/LICENSE) © [Heartex](https://www.heartex.com/). 2020
