Dark7Devil (aa)

Hey, great work. Since, you mentioned that you have used SYSPIN dataset for training, I wonder if there is a way to generate voices based on regions as well. Maybe Vaani dataset by IISC might help in this case well.

commented a paper 2 months ago

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Paper • 2510.16872 • Published Oct 19, 2025 • 106 •

4

liked a dataset 3 months ago

Homie0609/2026SoccerNetChallenge-VQA

Viewer • Updated Nov 12, 2025 • 329 • 86 • 3

commented 3 papers about 1 year ago

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published Nov 5, 2024 • 71 •

23

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published Nov 5, 2024 • 71 •

23

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

Paper • 2411.02959 • Published Nov 5, 2024 • 71 •

23

aa

AI & ML interests

Recent Activity

Organizations

Efficient MultiModal Data Pipeline

Dark7Devil/sbu_captions-hindi-english-pretrain

Dark7Devil/sbu_captions-hindi-english-pretrain

LingoIITGN/triveni-raw

Distilled model

MBZUAI-IFM/Llama-3.1-Nanda-87B-Chat

LingoIITGN/Triveni

vikhyatk/lnqa

Jina-VLM: Small Multilingual Vision Language Model

The Eiffel Tower Llama

merve/smol-vision

The Smol Training Playbook

DeepAnalyze: Agentic Large Language Models for Autonomous Data Science

Homie0609/2026SoccerNetChallenge-VQA

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

HtmlRAG: HTML is Better Than Plain Text for Modeling Retrieved Knowledge in RAG Systems

aa

AI & ML interests

Recent Activity

Organizations

Dark7Devil's activity

Efficient MultiModal Data Pipeline

Distilled model

The Eiffel Tower Llama

The Smol Training Playbook

🎉 Free Image Generator Now Available!