Audio Captioning on Clotho Caps (test)
29.4ScoreX-InstructBLIP
Evaluation results
| Method | Links | |
|---|---|---|
| X-InstructBLIPParams=189.91M+, All Modal=false, Data Size=27.78M+, Training Time=0.34s/it, GPU Memory=28.7G2024.10 | 29.4 | |
| OneLLMParams=7B+, All Modal=true, Data Size=1007M+, Training Time=0.83s/it, GPU Memory=64.8G2024.10 | 29.1 | |
| AnAParams=0.8~2.4M, All Modal=false, Data Size=23.2M+, Training Time=0.23s/it, GPU Memory=13.1G2024.10 | 28.6 | |
| ChatBridgeParams=7B+, All Modal=true, Data Size=4.4M+, Training Time=0.34s/it, GPU Memory=28.7G2024.10 | 26.2 |