sat-12l-sm is the small 12-layer transformer model from the Segment Any Text (wtpsplit) project. It performs state-of-the-art sentence boundary detection and token classification across 85 languages. The model is available in multiple formats including Transformers and ONNX and is designed for robust performance on real-world, noisy text data.
In the Other AI space, Sat 12l Sm takes a focused approach. Accurately segmenting text into sentences across many languages, including noisy or non-standard text where traditional rules fail. It is built as an open-source project for NLP developers and researchers. Sat 12l Sm is open source under the MIT license. The product ships for the web and API.
It is developed by Segment any Text, and the product first shipped in 2020. Development happens publicly on GitHub with 1.3k stars. Key capabilities include token classification, multilingual support, and ONNX export.
Latest indexed changes and source events
segment-any-text/sat-12l-sm verified by the PulseGate indexer
Other apps tracked under the same category.
