# Vedavani: A Benchmark Corpus for ASR on Vedic Sanskrit Poetry

arXiv: https://arxiv.org/abs/2506.00145 · HTML: https://mlsanity.com/paper/2506.00145/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 19 references that are in the map.
- First posted on arXiv 30 May 2025.

## Builds on (most cited first, 10 of 10)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden Units](https://mlsanity.com/paper/2106.07447/) (2021)
- [Unsupervised Cross-lingual Representation Learning for Speech Recognition](https://mlsanity.com/paper/2006.13979/) (2020)
- [Scaling Speech Technology to 1,000+ Languages](https://mlsanity.com/paper/2305.13516/) (2023)
- [Distil-Whisper: Robust Knowledge Distillation via Large-Scale Pseudo Labelling](https://mlsanity.com/paper/2311.00430/) (2023)
- [Towards Building ASR Systems for the Next Billion Users](https://mlsanity.com/paper/2111.03945/) (2021)
- [IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian languages](https://mlsanity.com/paper/2208.11761/) (2022)
- [Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASR](https://mlsanity.com/paper/2305.15386/) (2023)
- [Automatic Speech Recognition in Sanskrit: A New Speech Corpus and Modelling Insights](https://mlsanity.com/paper/2106.05852/) (2021)
- [Free as in Free Word Order: An Energy Based Model for Word Segmentation and Morphological Tagging in Sanskrit](https://mlsanity.com/paper/1809.01446/) (2018)

## Built on by (most cited first, 2 of 2)

- [Still Not There: Can LLMs Outperform Smaller Task-Specific Seq2Seq Models on the Poetry-to-Prose Conversion Task?](https://mlsanity.com/paper/2511.08145/) (2025)
- [Transformer-Enabled Diachronic Analysis of Vedic Sanskrit: Neural Methods for Quantifying Types of Language Change](https://mlsanity.com/paper/2512.05364/) (2025)

## Abstract (arXiv)

Sanskrit, an ancient language with a rich linguistic heritage, presents unique challenges for automatic speech recognition (ASR) due to its phonemic complexity and the phonetic transformations that occur at word junctures, similar to the connected speech found in natural conversations. Due to these complexities, there has been limited exploration of ASR in Sanskrit, particularly in the context of its poetic verses, which are characterized by intricate prosodic and rhythmic patterns. This gap in research raises the question: How can we develop an effective ASR system for Sanskrit, particularly one that captures the nuanced features of its poetic form? In this study, we introduce Vedavani, the first comprehensive ASR study focused on Sanskrit Vedic poetry. We present a 54-hour Sanskrit ASR dataset, consisting of 30,779 labelled audio samples from the Rig Veda and Atharva Veda. This dataset captures the precise prosodic and rhythmic features that define the language. We also benchmark the dataset on various state-of-the-art multilingual speech models.1 Experimentation revealed that IndicWhisper performed the best among the SOTA models.