News for hackers. Stuff that matters.
Re:Ask HN: Could we skip speech to text using vector databases? by minimaxir on Thursday February 29, 2024 @12:54PM (#39552634)
It is possible to create audio/speech embeddings using a model like CLAP: https://huggingface.co/laion/larger_clap_music_and_speech

The results aren't good for nearest neighbor vector lookup, however.

There are no comments on this comment yet.