MultiIndic WikiBio Unified Script
This biography generation release fine-tunes IndicBART on the corresponding IndicNLG dataset. It supports 9 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 biography generation; it is not a general conversation model.MultiIndic WikiBio Unified Script official model card
Review the generated text against its input
Practical guidance. Use a source record with names, dates and occupations. Check generated statements against that record; fluent prose is not evidence for a new biographical fact.
Specifications & access
| Detail | Value and conditions |
|---|---|
| Access | Downloadable |
| Model identifiers | MultiIndicWikiBioUnified |
| Input scripts | Indian-language text is mapped to Devanagari.MultiIndic WikiBio Unified Script official model card |
| Training set | 34,653 examplesMultiIndic WikiBio Unified Script official model card |
| License | MIT in the model card.MultiIndic WikiBio Unified Script official model card |
Related models
Multilingual generation model that maps Indian-language text into shared Devanagari script.
Launch date not confirmedDownloadable- MultiIndic WikiBio Separate Scripts
AI4Bharat · IndicNLG
Separate-script IndicBART adaptation for biography generation in nine Indian languages.
Launch date not confirmedDownloadable