Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Audio Flamingo (Pengi trainset)

Audio Flamingo (Pengi trainset)

Reported on 6 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Audio6 results

Audio captioningonClotho
BLEU-4· uses extra data· 2024-02-02
17.4
best: 19 (VAST)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831
Audio captioningonClotho
CIDEr· uses extra data· 2024-02-02
0.489
best: 14 (ZerAuCap)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831
Audio captioningonClotho
METEOR· uses extra data· 2024-02-02
18.7
best: 19.3 (VAST)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831
Audio captioningonClotho
ROUGE-L· uses extra data· 2024-02-02
39.4
best: 40.8 (VAST)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831
Audio captioningonClotho
SPICE· uses extra data· 2024-02-02
0.134
best: 5.3 (ZerAuCap)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831
Audio captioningonClotho
SPIDEr· uses extra data· 2024-02-02
0.312
best: 9.7 (ZerAuCap)
Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities arXiv:2402.01831