1 42

Hiroaki OGASAWARA

xhiroga

AI & ML interests

None yet

Recent Activity

liked a dataset about 1 month ago

DataPilot/AItuber-Personas-Japan

liked a model 3 months ago

deepseek-ai/DeepSeek-OCR-2

liked a Space 3 months ago

Qwen/Qwen3-TTS

View all activity

Organizations

liked a dataset about 1 month ago

DataPilot/AItuber-Personas-Japan

Viewer • Updated Mar 16 • 195 • 324 • 28

liked a model 3 months ago

deepseek-ai/DeepSeek-OCR-2

Image-Text-to-Text • 3B • Updated Feb 3 • 1.45M • 930

liked a Space 3 months ago

Qwen3-TTS Demo

🎙

1.91k

Generate speech audio from text with custom or cloned voices

updated a dataset 4 months ago

xhiroga/data

Viewer • Updated Jan 3 • 1 • 8 • 1

liked a dataset 5 months ago

Seed3D/Articulation-XL2.0

Updated Sep 19, 2025 • 288 • 32

liked a model 5 months ago

VAST-AI/UniRig

Updated Aug 1, 2025 • 82

liked a model 6 months ago

microsoft/Phi-4-multimodal-instruct

Automatic Speech Recognition • 6B • Updated Dec 10, 2025 • 375k • 1.6k

liked a Space 6 months ago

Open ASR Leaderboard

🏆

1.33k

Explore and compare speech‑recognition model benchmarks

liked a model 6 months ago

nguyenvulebinh/AV-HuBERT-MuAViC-multilingual

Text Generation • 0.4B • Updated Mar 6, 2025 • 46 • 2

liked a model 7 months ago

meta-llama/Llama-3.2-3B

Text Generation • 3B • Updated Oct 24, 2024 • 1.11M • 763

upvoted a paper 7 months ago

Zero-AVSR: Zero-Shot Audio-Visual Speech Recognition with LLMs by Learning Language-Agnostic Speech Representations

Paper • 2503.06273 • Published Mar 8, 2025 • 6

liked a model 7 months ago

fierce-cats/beatrice-trainer

Audio-to-Audio • Updated Aug 30, 2025 • 39

updated a dataset 8 months ago

xhiroga/hiroga-speech

Updated Sep 14, 2025 • 7

published a dataset 8 months ago

xhiroga/hiroga-speech

Updated Sep 14, 2025 • 7

liked 3 models 9 months ago

liked 2 Spaces 9 months ago

LLM Embeddings Explained: A Visual and Intuitive Guide

🚀

341

How Language Models Turn Text into Meaning, From Traditional

Mitsua Likes Demo

🚀

Text-to-Image Diffusion Model trained on licensed/pd data