The digitization of classical Sanskrit literature is impeded by a scarcity of annotated resources, particularly for Named Entity Recognition (NER). While recent methodologies utilize generic Large Language Models (LLMs) for data augmentation, these approaches remain prone to error and often lack the reasoning depth required for classical grammar. In this work, we introduce Naamah, a high quality silver standard Sanskrit NER dataset comprising 102,942 sentences. We propose a methodology that combines entity extraction from DBpedia with the generative capabilities of a 24B parameter hybrid reasoning model to create grammatically natural and synthetically diverse training data. We utilize this dataset to benchmark two transformer architectures: the massive multilingual XLM RoBERTa and the parameter efficient IndicBERTv2. Our experiments reveal a key insight: while both models scale well with synthetic data, IndicBERTv2 qualitatively outperforms XLM RoBERTa in entity identification and classification. On a fixed split of 92,647 train and 10,295 validation examples, IndicBERTv2 achieves the best validation F1 of 0.9615, outperforming XLM R’s 0.9506 while remaining substantially lighter for deployment. We demonstrate that the generic tokenizer of XLM R fractures Sanskrit terms, whereas the domain adapted tokenizer of IndicBERTv2 preserves semantic integrity.

Text Generation has achieved remarkable performance using large language models. It has also been recently well-studied that these large language models are capable of creative generation tasks but prominently for high-resource languages. This prompts a fundamental question: Is there a way to utilize these (large) language models for structured poetry generation in a low-resource language, such as Sanskrit? We present Chandomitra, an English input to structured Sanskrit Poetry translation dataset, specifically adhering to the Anushtubh meter. We benchmark various open and closed models, and scrutinize specialized techniques such as constrained decoding and instruction fine-tuning, for the proposed task. Our constrained decoding methodology achieves 99.86% syntactic accuracy in generating metrically valid Sanskrit poetry, outperforming GPT-4o (1-shot: 31.24%). Our best-performing instruction-tuned model, on the other hand, performs better in semantic coherence with the English input, at the expense of slightly lower syntactic accuracy. Human evaluation further reveals that instruction fine-tuned model is better able to capture the poetic aspects.

The Rigveda, among the oldest Indian texts in Vedic Sanskrit, employs a distinctive pitchaccent system - udatta, anudatta, svarita whose marks encode melodic and interpretive cues but are often absent from moderne-texts. This work develops a parallel corpus of accented-unaccented ́slokas and conducts a controlled comparison of three strategies for automatic accent placement in Rigvedic verse: (i) full fine-tuning of ByT5, a byte-level Transformer that operates directly on Unicode combining marks, (ii) a from-scratch BiLSTM-CRF sequence-labeling baseline, and (iii) LoRA-based parameter-efficient fine-tuning atop ByT5. Evaluation uses Word Error Rate (WER) and Character Error Rate (CER) for orthographic fidelity, plus a task-specific Diacritic Error Rate (DER) that isolates accent edits. Full ByT5 fine-tuning attains the lowest error across all metrics; LoRA offers strong efficiencyaccuracy trade-offs, and BiLSTM-CRF serves as a transparent baseline. The study underscores practical requirements for accent restoration - Unicode-safe preprocessing, mark-aware tokenization, and evaluation that separates grapheme from accent errors - and positions heritage-language technology as an emerging NLP area connecting computational modeling with philological and pedagogical aims. Results establish reproducible baselines for Rigvedic accent restoration and provide guidance for downstream tasks such as accentaware OCR, ASR/chant synthesis, and digital scholarship.