A large-scale Automatic Speech Recognition (ASR) model for Tamil, utilizing a hybrid CTC-RNNT decoder.
The indicconformer_stt_ta_hybrid_ctc_rnnt_large model is designed for automatic speech recognition (ASR) in Tamil. It uses a Conformer-Large architecture with 120 million parameters, featuring 17 conformer blocks. This model processes 16 kHz mono-channel audio (wav files) and produces Tamil transcriptions. Its hybrid CTC-RNNT decoder improves recognition performance for spoken Tamil.
MIT
AI4Bharat
Audio-to-text
N.A.
Open
Sector Agnostic
21/02/25 13:21:29
0
MIT
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.