Automated Audio Captioning state-of-the-art scores

SPIDEr as the function of the number of parameters,
for the AudioCaps (AC) dataset.

SPIDEr as the function of the years,
for the AudioCaps (AC) dataset.

SPIDEr as the function of the number of parameters,
for the Clotho (CL) dataset.

SPIDEr as the function of the years,
for the Clotho (CL) dataset.

Automated Audio Captioning SOTA