🔄 In a Training Loop

Ashish Chadha

Neural-Hacker

·

AI & ML interests

Building AI for Bharat

Recent Activity

liked a dataset about 19 hours ago

liked a model 5 days ago

luminenio/gnani-evon-v3.3-30B-A3B-GGUF

published a bucket 7 days ago

Neural-Hacker/indic-diarbench-bucket

View all activity

Organizations

upvoted a collection 9 days ago

Bodhan September 2026

Collection of multilingual, multimodal models released as part of 5 Sep 2026 release • 5 items • Updated 10 days ago • 8

upvoted an article 10 days ago

Article

A Real-World Dataset for Noise-Robust Speech AI: 100+ Timestamped Noise Types Across 58 Indian Languages

ARTPARK-IISc

•

10 days ago

• 3

upvoted 2 articles 28 days ago

Article

Fine-Tune SraVaani on Your Own Speech Data

ARTPARK-IISc

•

Aug 11

• 6

Article

SraVaani: How Vision Helps Hearing

ARTPARK-IISc

•

Aug 11

• 6

upvoted a collection 28 days ago

SraVaani

2 items • Updated Aug 7 • 2

upvoted 2 papers about 1 month ago

SraVaani 1.0: Scaling Inclusive Speech Recognition for Indic Languages

Paper • 2608.08235 • Published Aug 8 • 2

Dynamic Multi-Expert Projectors with Stabilized Routing for Multilingual Speech Recognition

Paper • 2601.19451 • Published Jan 27 • 1

upvoted 3 collections about 1 month ago

Nandi-Mini-GuardRails

2 items • Updated Jul 23 • 4

Nandi-Mini

Nandi-Series of Mini Models • 5 items • Updated Jul 23 • 12

Lumma

4 items • Updated 24 days ago • 5

upvoted an article about 2 months ago

Article

svara-TTS — Open Multilingual TTS for India’s Voices

kenpath

•

Oct 27, 2025

• 26

upvoted a collection 3 months ago

NCERT_Dataset

The NCERT dataset is a collection of educational content derived from NCERT textbooks for students in standards 6 to 12. • 33 items • Updated Mar 2 • 9

upvoted 2 papers 3 months ago

Grouped Query Experts: Mixture-of-Experts on GQA Self-Attention

Paper • 2606.20945 • Published Jun 18 • 81

LeafNet: A Large-Scale Dataset and Comprehensive Benchmark for Foundational Vision-Language Understanding of Plant Diseases

Paper • 2602.13662 • Published Feb 14 • 1

upvoted 6 collections 3 months ago

RomanSetu

Romansetu is a collection of models address the challenge of extending Large Language Models (LLMs) to non-English languages using non-Latin scripts • 11 items • Updated Mar 7, 2025 • 5

IndicRagSuite

A comprehensive dataset collection for Indic language information retrieval. • 2 items • Updated Mar 2 • 3

CIA Suite

Hercule series of Evaluation models • 16 items • Updated Oct 22, 2024 • 2

IndicLLMSuite

Largest Collections of Pretraining and Instruction Finetuning datasets for 22 Indic languages. • 4 items • Updated Nov 5, 2024 • 20

IndicConformer

A collection of ASR models for 22 scheduled languages of India • 23 items • Updated Mar 2 • 42

Airavata Evaluation Suite

A collection of benchmarks used for evaluation of Airavata, an Hindi instruction-tuned model on top of Sarvam's OpenHathi base model. • 20 items • Updated Mar 2 • 10