Japanese SFT/DPO data convert to speech via TTS. And audio caption data generated by Qwen3-Omni. All datasets are available for commercial use.
Ayuto Tsutsumi
Atotti
AI & ML interests
None yet
Recent Activity
published a model about 5 hours ago
Atotti/Ja-FastConformer-CTC-25Hz-Streaming-100M liked a model 2 days ago
thinkingmachines/Inkling-Small liked a model 2 days ago
ly-corporation/PASQAOrganizations
models 31
Atotti/Ja-FastConformer-CTC-25Hz-Streaming-100M
Automatic Speech Recognition • Updated • 1
Atotti/llm-jp-4-8b-speech-asr
Automatic Speech Recognition • 9B • Updated • 67 • 5
Atotti/llm-jp-4-8b-speech-chat
Audio-Text-to-Text • 9B • Updated • 20 • 11
Atotti/xacle-tmu-2026
Audio-Text-to-Text • Updated • 15
Atotti/LlamaForSpeechLM-ja-Instruct-Full-step10000
9B • Updated
Atotti/LlamaForSpeechLM-ja-Instruct-Full-step20000
9B • Updated
Atotti/LlamaForSpeechLM-ja-DPO-Full-step3500
9B • Updated
Atotti/LlamaForSpeechLM-ja-Instruct-Full-step37000
9B • Updated
Atotti/LlamaForSpeechLM-ja-DPO-Full-step8000
9B • Updated
Atotti/LlamaForSpeechLM-ja-DPO-Full-step1000
9B • Updated
datasets 10
Atotti/segment-sidecar-v1
Viewer • Updated • 256 • 7
Atotti/fsd50k-ccby-Qwen3-Omni-captioned
Viewer • Updated • 23.5k • 32
Atotti/spoken-multiturn-sft
Viewer • Updated • 59.1k • 247
Atotti/spoken-dpo-49k
Viewer • Updated • 43.1k • 107
Atotti/fsd50k-cc0-Qwen3-Omni-captioned
Viewer • Updated • 19.9k • 27
Atotti/spoken-magpie-ja
Viewer • Updated • 132k • 599 • 1
Atotti/audiocaps-ja
Viewer • Updated • 57.2k • 34
Atotti/clotho-ja
Viewer • Updated • 19.7k • 223
Atotti/VTuber-overview-split
Viewer • Updated • 2.94k • 39 • 1
Atotti/VTuber-overview
Viewer • Updated • 420 • 21