This Automatic Speech Recognition (ASR) model is designed for Kashmiri speech recognition. It processes 16,000 KHz mono WAV audio files and converts spoken content into text. The model follows a Conformer-Large architecture, featuring a 120M-parameter encoder combined with a hybrid CTC-RNNT decoder. It consists of 17 conformer blocks with a model dimension of 512, ensuring efficient and accurate transcription of Kashmiri speech.
MIT
Sector Agnostic
AI4Bharat
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
N.A.
Open
21/02/25 13:21:43
N.A.
0
© 2026 - Copyright AIKosh. All rights reserved.