AI4BharatIndicNLG
MultiIndic Paraphrase Generation Separate Scripts
This paraphrasing release fine-tunes IndicBARTSS on the corresponding IndicNLG dataset. It supports 11 Indian languages.
The task fine-tune is separate from the pretrained model
Its separate-script design follows the base model. No Devanagari round trip is needed. The release is intended for paraphrasing; it is not a general conversation model.MultiIndic Paraphrase Generation Separate Scripts official model card
Review the generated text against its input
Practical guidance. Compare meaning as well as wording. Keep negation, quantities and named entities unchanged when a paraphrase must preserve the original claim.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | MultiIndicParaphraseGenerationSS |
| Input scripts | Native scripts are retained.MultiIndic Paraphrase Generation Separate Scripts official model card |
| Training set | 5.53 million sentencesMultiIndic Paraphrase Generation Separate Scripts official model card |
| License | MIT in the model card.MultiIndic Paraphrase Generation Separate Scripts official model card |
Related models
- IndicBART Separate Scripts
AI4Bharat · IndicBART
IndicBART generation variant that retains each Indian language's own script.
Launch date not confirmedDownloadable Unified-script IndicBART adaptation for paraphrase generation in 11 Indian languages.
Launch date not confirmedDownloadable