Open voodoohop opened 2 years ago
we have an ongoing project at laion discord (https://discord.gg/eq3cAMZtCC) to try and make a good AudioClip and also to collect a larger text/audio dataset
once these 2 bricks are available, indeed building a semantic search system will be very fun!
I have just been evaluating wav2clip in combination with image generation. It embeds to the same embedding space as CLIP VIT-B/32 and seems to be working really well for me.
we have an ongoing project at laion discord (https://discord.gg/eq3cAMZtCC) to try and make a good AudioClip and also to collect a larger text/audio dataset
once these 2 bricks are available, indeed building a semantic search system will be very fun!