Su-śrotā is an open Sanskrit automatic speech-recognition model fine-tuned on śāstric and recitational speech, including chant and prose. Developers can load it with NVIDIA NeMo for local audio transcription and integrate it into Sanskrit language applications.
Sushrota Sanskrit Asr is a Speech to text project. It focuses on transcribing Sanskrit chanting and prose when general-purpose speech recognition performs poorly. Sushrota Sanskrit Asr is an open-source project aimed at sanskrit researchers, developers, and practitioners building speech-transcription tools. The project is open source (Open Source). Sushrota Sanskrit Asr is available on the web, the command line, and API, and it can be self-hosted.
Behind Sushrota Sanskrit Asr is prathoshap, and it first shipped in 2026. Development happens publicly on GitHub with 68 stars and 3 commits in the last 90 days. Among its 6 catalogued features are audio transcription, chant recognition, and prose recognition.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Same category — not a similarity match