A Scrutinized Survey on the Accuracy & Availability of Sanskrit Translation Models

Deep learning is the subset of Machine learning (ML), the new advanced AI technology of that involves training the artificial neural networks with many layers (hence ‘deep’) to learn from input data. Language translation is one of the vast fields of NLP which involves translating text from one language to other language, conserving the meaning of the input text, and producing fluent text in the output language. The initiative behind machine translation is to build up computer algorithms and to execute computer programs that will allow a computer to automatically translate human language from one language to another language without any human involvement during the translation process. This results to the formation of ‘Translation Models’ which are designed to explain the mathematical relationship between two or more languages. They are called models of translational equivalence because the main thing that they aim to predict is whether expressions in different languages have equivalent meanings or not. This manuscript focuses on the one of the most ancient and sacred language, Sanskrit found in almost all the holy books of Indian religion like Hinduism, Buddhism and Jainism. Jain narrative literature is found in Sanskrit, Prakrat and Apabhramsa which is rightly recognized as one of the South Asia’s great cultural heritages and a vital source of material for insight into pre modern Jain teachings, practices and everyday life. New AI model claims to translate 200 languages, making the technology accessible to more people. Is sanskrit a part of 200 languages? Can we rely on this new AI for accurate translations?This manuscript lays out the following surveys-•Existence of Translation models for Jain Literature present in Prakrit and Apbhramsa•Sanskrit translation models like Google translator, Glosbe translate etc. and their comparison (if any)•Accuracy of word and phrase translation from Sanskrit to hindi/english•Speech to Text or Text to Speech models to read Sanskrit literature•Algorithmic structure of Stemming and Lemmatization of Sanskrit words in NLP