Government Of India
A-
A
A+
AI4Bharat-IndicConformer-STT-SAT-Hybrid-CTC-RNNT-Large (Santali): Automatic Speech Recognition Model
A large-scale Automatic Speech Recognition (ASR) model for Santali, utilizing a hybrid CTC-RNNT decoder.
About Model
The ai4bharat/indicconformer_stt_sat_hybrid_ctc_rnnt_large model is an Automatic Speech Recognition (ASR) system designed for the Santali language. It employs a Conformer-Large architecture with 120 million parameters, featuring 17 conformer blocks and a model dimension of 512. This model processes 16 kHz mono-channel audio (wav files) and outputs transcriptions in Santali. Its hybrid CTC-RNNT decoder enhances recognition performance for spoken Santali.
AI4Bharat-IndicConformer-STT-SAT-Hybrid-CTC-RNNT-Large (Santali): Automatic Speech Recognition Model
Metadata
MIT
AI4Bharat
Audio-to-text
N.A.
Open
Sector Agnostic
21/02/25 13:21:31
0
Activity Overview
0
18 
0 
458
Tags
- Automatic Speech Recognition
- Conformer
- Hybrid-CTC-RNNT
- ASR
- Speech-to-Text
- Deep Learning
- Neural Networks
- Speech Recognition
- Indic Languages
License Control
MIT
More Models from AI4Bharat
AI4Bharat- 500 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
AI4Bharat- 400 M - RomanSetu Multilingual Native-to-Roman Model
RomanSetu is a multilingual continual pretrained transformer model designed for transliteration across six Indic languages
AI4Bharat- Maithili - IndicConformer Automatic Speech Recognition (ASR) Model
This model takes in mono-channel audio files at a 16,000 Hz sampling rate (WAV format) and outputs the transcribed text of the speech contained in the audio.
Automatic Speech Recognition
Speech-to-Text
NLP
- 0
- 22
- 0
541
Updated 9 month(s) ago
AI4BHARAT
AI4Bharat- Konkani - IndicConformer Automatic Speech Recognition (ASR) Model
Automatic Speech Recognition (ASR) model for Konkani speech recognition, processing 16,000 KHz mono WAV audio and transcribing spoken content into text
Speech-to-Text
NLP
Automatic Speech Recognition
- 0
- 27
- 0
- 566
Updated 9 month(s) ago
AI4BHARAT
AI4Bharat- Kashmiri - IndicConformer Automatic Speech Recognition (ASR) Model
This Automatic Speech Recognition (ASR) model transcribes Kashmiri speech from 16,000 KHz mono WAV audio files into text
Kashmiri
Speech-to-Text
NLP
Automatic Speech Recognition
- 0
- 17
- 0
- 542
Updated 9 month(s) ago
AI4BHARAT
AI4Bharat - Romansetu-200M -Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
AI4Bharat - Romansetu-100M - Multilingual LLM for Indian langauges using romanization
RomanSetu is Efficiently unlocking multilingual (Indian Languages) capabilities of Large Language Models via Romanization.
AI4Bharat- Kannada - IndicConformer Automatic Speech Recognition (ASR) Model
This Kannada Automatic Speech Recognition (ASR) model transcribes 16kHz mono-channel audio into text. It utilizes a Conformer-Large architecture with 120M parameters and a hybrid CTC-RNNT decoder for high-accuracy speech recognition.
Automatic Speech Recognition
Audio Processing
NLP
- 0
- 19
- 0
- 544
Updated 9 month(s) ago
AI4BHARAT
AI4Bharat – Romanized Path – Base to Supervised Fine-Tuning (SFT)
Romansetu model is built on base pretrained model which is supervised fine tuned on instuction-following tasks using romanized Indian languages.
AI4Bharat-IndicTrans2 Large-1B -English-to-Hindi (Devanagari) – : Language Translation Model
A large-scale neural machine translation (NMT) model for translating English to Hindi (Devanagari) language, leveraging 1 billion parameters for high-quality translations.
Machine Translation
Transformer
low-resource-NLP
high-quality-translation
Large Model
cross-lingual
NLP
Multilingual
- 0
- 28
- 0
- 653
Updated 9 month(s) ago
AI4BHARAT
© 2026 - Copyright AIKosh. All rights reserved. This portal is developed by National e-Governance Division for AIKosh mission.