Indic AI Models - a ranjithraj Collection

ranjithraj 's Collections

updated Jul 22

Open-source AI for Indian languages — LLMs, ASR, TTS, speech translation, encoders, VLMs, and datasets across 22 Indic languages.

Upvote

sarvamai/sarvam-30b

Text Generation • 32B • Updated Mar 23 • 14.5k • 222
sarvamai/sarvam-1

Text Generation • 3B • Updated Nov 8, 2024 • 8.11k • 146
bharatgenai/Param-1-7B

7B • Updated Jan 8 • 226 • 4
bharatgenai/Param2-17B-A2.4B-Thinking

Text Generation • 17B • Updated 4 days ago • 12.6k • 77
budecosystem/hex-1

Text Generation • 4B • Updated May 6, 2025 • 31 • 3
FrontiersMind/Nandi-Mini-150M

Text Generation • 0.2B • Updated May 15 • 272 • 141
vasista22/whisper-telugu-large-v2

Automatic Speech Recognition • Updated Apr 24, 2023 • 937 • 11
ARTPARK-IISc/Vaani-FastConformer-Telugu

Automatic Speech Recognition • Updated Apr 2 • 12
SPRINGLab/Indic-Mio

Text-to-Speech • 0.6B • Updated May 27 • 8.56k • 28
ai4bharat/IndicF5

Text-to-Speech • 0.4B • Updated Mar 3 • 26.9k • 184
ai4bharat/indic-seamless

Automatic Speech Recognition • 2B • Updated Mar 7, 2025 • 4.49k • 21
ai4bharat/IndicBERT-v3-270M

Token Classification • 0.3B • Updated Jun 12 • 232 • 4
krutrim-ai-labs/Chitrarth

Image-Text-to-Text • 8B • Updated Mar 26, 2025 • 145 • 18
ai4bharat/IndicVoices

Viewer • Updated Jun 15 • 6.38M • 21.2k • 99
ai4bharat/sangraha

Viewer • Updated Mar 5, 2025 • 268M • 18.9k • 83
ai4bharat/indic-conformer-600m-multilingual

Automatic Speech Recognition • Updated Feb 7 • 69.7k • 127

Note Conformer CTC/RNNT ASR for 22 Indic languages (600M)
ai4bharat/indic-parler-tts

Text-to-Speech • 0.9B • Updated Sep 24, 2025 • 351k • 313

Note TTS for Indic languages using Parler-TTS architecture
ai4bharat/indicwav2vec-hindi

Automatic Speech Recognition • Updated Jul 27, 2022 • 5.25k • 25

Note Self-supervised wav2vec2 pretrained on Hindi
ARTPARK-IISc/SraVaani-1.0

Automatic Speech Recognition • Updated 18 days ago • 5.28k • 74

Note FastConformer TDT-CTC ASR for 63 Indian languages
swechatelangana/swecha-gonthuka-asr

Automatic Speech Recognition • 94.4M • Updated Feb 21 • 204 • 7

Note Community Telugu wav2vec2-CTC ASR model
ai4bharat/Airavata

Text Generation • 7B • Updated Mar 11, 2024 • 1.66k • 39

Note Indic language LLM by AI4Bharat
sarvamai/sarvam-m

Text Generation • 24B • Updated May 28, 2025 • 4.49k • • 348

Note Sarvam AI's multilingual model for Indian languages
sarvamai/sarvam-translate

Translation • 4B • Updated Jul 13 • 11.5k • 155

Note Translation model for Indian languages
ai4bharat/IndicBERT-v3-1B

Token Classification • 1.0B • Updated Jun 12 • 25 • 7

Note 1B parameter BERT for 23 Indian languages
ai4bharat/IndicBERTv2-MLM-only

Fill-Mask • Updated Sep 5, 2024 • 30.3k • • 10

Note BERT MLM for 12 major Indian languages
ai4bharat/IndicNER

Token Classification • Updated Dec 21, 2022 • 9.23k • 34

Note Named Entity Recognition for 11 Indian languages
ai4bharat/indictrans2-indic-en-1B

Translation • 1B • Updated May 2, 2025 • 9.07k • 46

Note Indic→English translation (1B params)
ai4bharat/indictrans2-en-indic-1B

Translation • 1B • Updated May 2, 2025 • 10.4k • 62

Note English→Indic translation (1B params)
ai4bharat/indictrans2-indic-indic-1B

Translation • 1B • Updated May 2, 2025 • 1.28k • 14

Note Indic↔Indic translation (1B params)
ai4bharat/indictrans2-indic-en-dist-200M

Translation • 0.2B • Updated May 2, 2025 • 10.6k • 22

Note Distilled Indic→English translation (200M)
ai4bharat/indictrans2-en-indic-dist-200M

Translation • 0.3B • Updated May 2, 2025 • 29.3k • 38

Note Distilled English→Indic translation (200M)
ai4bharat/IndicBART

Updated Aug 7, 2022 • 256k • 40

Note Denoising autoencoder for 12 Indic languages
parthiv11/indic_whisper_nodcil

Automatic Speech Recognition • Updated Feb 28, 2024 • 443 • 11

Note Indic Whisper fine-tune (no DCIL)
kavyamanohar/AI4B-Indicwhisper-ml

0.8B • Updated May 7, 2025 • 43

Note Indic Whisper fine-tune for Malayalam

Upvote