Dataset and checkpoints for TEMPO: timestamped ASR, diarization, audio grounding, dense captioning and music captioning.
Jayakumar
Kaousheik
·
AI & ML interests
None yet
Recent Activity
updated a model 4 days ago
Kaousheik/tempo-ablation-both updated a model 4 days ago
Kaousheik/tempo-ablation-projector updated a model 4 days ago
Kaousheik/tempo-ablation-lossOrganizations
models 10
Kaousheik/tempo-ablation-both
Audio-Text-to-Text • 8B • Updated • 47
Kaousheik/tempo-ablation-projector
Audio-Text-to-Text • 8B • Updated • 52
Kaousheik/tempo-ablation-loss
Audio-Text-to-Text • 8B • Updated • 46
Kaousheik/tempo-ablation-naive
Audio-Text-to-Text • 8B • Updated • 40
Kaousheik/tempo-rl-singletask-music
Audio-Text-to-Text • 8B • Updated • 48
Kaousheik/tempo-rl-multitask
Audio-Text-to-Text • 8B • Updated • 46
Kaousheik/tempo-sft-stage1-2
Audio-Text-to-Text • 8B • Updated • 50
Kaousheik/tempo-sft-stage2-realonly
Audio-Text-to-Text • 8B • Updated • 52
Kaousheik/tempo-sft-stage1
Audio-Text-to-Text • 8B • Updated • 55
Kaousheik/hanabi-gpt-oss
120B • Updated • 4