AFWhisper Pretraining Weights

#7
by primus-pablo - opened

Thank you for the great work, and for making everything publicly available!

I’m particularly interested in exploring the AF-Whisper audio representations before and after reasoning fine-tuning. Would it be possible to share a checkpoint of the AF-Whisper model that was trained only for audio captioning, along with the corresponding transformer text decoder?

Many thanks in advance for your time and help.

Best,
Paul

Sign up or log in to comment