AI4BharatIndicNLG
MultiIndic Sentence Summarization Unified Script
This sentence summarization release fine-tunes IndicBART on the corresponding IndicNLG dataset. It supports 11 Indian languages.
The task fine-tune is separate from the pretrained model
Its unified-script design follows the base model. Non-Devanagari input and output require script conversion. The release is intended for sentence summarization; it is not a general conversation model.MultiIndic Sentence Summarization Unified Script official model card
Review the generated text against its input
Practical guidance. Review omissions as well as factual changes. A shorter sentence can remove the condition that made the original statement correct.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | MultiIndicSentenceSummarization |
| Input scripts | Indian-language text is mapped to Devanagari.MultiIndic Sentence Summarization Unified Script official model card |
| License | MIT in the model card.MultiIndic Sentence Summarization Unified Script official model card |
Related models
Multilingual generation model that maps Indian-language text into shared Devanagari script.
Launch date not confirmedDownloadableSeparate-script IndicBART model for sentence summaries in 11 Indian languages.
Launch date not confirmedDownloadable