Nepali speech data collection for TTS & STT
Steer PaliGemma's vision model from the inside (SAE)
Maithili text-to-speech (VITS, fine-tuned MMS-TTS)
Audited memory for AI agents — MCP + portal, one Space
Analyze and compare images with a universal vision encoder
Transcribe Maithili audio to text
Graph-Visualize
Create a video from an audio file and image with visual effects
embedding-model
Extract Text for low resource.
Nepali Speech To Text
tts Nepali
NepaliOCR
ocr_nepali