ai4bharat/IndicBART is a multilingual BART-based model trained on 11 Indian languages plus English. It excels at machine translation, summarization, and other sequence-to-sequence tasks for Indic languages. The model is openly available on Hugging Face and has been widely downloaded for research and application development.
In the Other models space, IndicBART takes a focused approach. It focuses on providing high-quality machine translation and text generation support for low-resource Indian languages. It is built as an open-source project for developers. The project is open source (MIT). It runs on the web and API.
AI4Bharat builds and maintains IndicBART, and it first shipped in 2021. The project is developed in the open on GitHub with 51 stars. Among its 3 catalogued features are Multilingual Translation, Indic Languages, and sequence-to-Sequence.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do