Zero-shot audio captioning with audio-language model guidance and audio context keywords

Benchmark Model Rank Results
zero-shot-audio-captioning-on-audiocapsZerAuCap#2METEOR: 12.3BLEU-4: 6.8CIDEr: 28.1ROUGE-L: 33.1SPICE: 8.6…
zero-shot-audio-captioning-on-audiocapsNo audio (baseline)#3METEOR: 4.1BLEU-4: 0CIDEr: 0.1ROUGE-L: 17.8SPICE: 0SPIDEr: 0