arxiv:2602.00130
Sumit Yadav
rockerritesh
AI & ML interests
AI(GAN) || LLM RAG
Recent Activity
liked a model about 17 hours ago
himalaya-ai/himalaya-gemma-4-e2b-it liked a model 3 days ago
yuxinlu1/gemma-4-12B-coder-fable5-composer2.5-v1-GGUF updated a model 3 days ago
rockerritesh/speakright-modelsOrganizations
spaces 22
pinned
Sleeping
NepalVoice
🎙
Nepali speech data collection for TTS & STT
Paused
Agents
Visual Steerability
🎛
Steer PaliGemma's vision model from the inside (SAE)
Running
Maithili TTS
🗣
Maithili text-to-speech (VITS, fine-tuned MMS-TTS)
Running
1
Tatva
🧠
Audited memory for AI agents — MCP + portal, one Space
Paused
Agents
1
EUPE Vision Encoder
🔍
Analyze and compare images with a universal vision encoder
Sleeping
Agents
1
Maithili Asr
🌖
Transcribe Maithili audio to text
models 18
rockerritesh/speakright-models
Updated
rockerritesh/nepali-ocr-Nepali-and-English
Updated
rockerritesh/smollm2-135m-fineweb-edu-200m
Text Generation • 0.1B • Updated • 6
rockerritesh/gpt2-small-fineweb-edu-200m
Text Generation • 0.1B • Updated • 8
rockerritesh/EUPE-ONNX
Image Feature Extraction • Updated • 1
rockerritesh/whisper-tiny-maithili
Automatic Speech Recognition • 37.8M • Updated • 6
rockerritesh/maiBERT_TF
Text Classification • Updated • 110 • 1
rockerritesh/paligemma_ne
3B • Updated • 9
rockerritesh/NepaliSentiment
Text Classification • Updated
rockerritesh/tr_OCR_handwritten
28.9M • Updated