Retrieval Augmented Few Shot In Context Audio
Metrics
CIDEr
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | CIDEr |
|---|---|
| recap-retrieval-augmented-audio-captioning | 0.359 |
| prefix-tuning-for-automated-audio-captioning | 0.211 |
| audio-captioning-transformer | 0.149 |
| automated-audio-captioning-by-fine-tuning | 0.147 |
| audio-flamingo-a-novel-audio-language-model | 0.518 |