Hour-scale timestamped audio captioning and speech diarization: BF16 and FP8 checkpoints and the long-form benchmark.
Jinchuan Tian PRO
JinchuanTian
AI & ML interests
None yet
Recent Activity
published a dataset 4 days ago
JinchuanTian/LongCapBench-TAC-Long published a model 4 days ago
JinchuanTian/LongCap-35B-A3B published a model 4 days ago
JinchuanTian/LongCap-35B-A3B-FP8Organizations
models 6
JinchuanTian/LongCap-35B-A3B
Audio-Text-to-Text • 35B • Updated • 63
JinchuanTian/LongCap-35B-A3B-FP8
Audio-Text-to-Text • 35B • Updated • 60 • 2
JinchuanTian/opuslm-sft
Updated
JinchuanTian/owsm_en
Updated
JinchuanTian/opuslm_v1_7b_anneal_205
Updated
JinchuanTian/OpusLM_v0_1.7B_NAACL_Demo
Updated • 1
datasets 19
JinchuanTian/LongCapBench-TAC-Long
Updated • 54 • 1
JinchuanTian/mmau-mmar-audio-detective
Viewer • Updated • 10k • 29
JinchuanTian/ytdl
Updated • 10
JinchuanTian/airbench
Viewer • Updated • 292 • 30
JinchuanTian/audiobench
Viewer • Updated • 11.6k • 236
JinchuanTian/eval_data
Viewer • Updated • 47.2k • 590
JinchuanTian/librispeech-test-clean-plain-tts
Viewer • Updated • 2.62k • 94
JinchuanTian/mmau_generation_test
Viewer • Updated • 995 • 93
JinchuanTian/mmau_test_mini
Updated • 7
JinchuanTian/Bagpiper_checkpoints
Updated • 5