NatureLM-audio: Getting Started
NatureLM-audio is the first large audio-language model tailored specifically for bioacoustics. The model has been open-sourced on Hugging Face, and we are continuing to make improvements as we get more feedback from our community!
Quick Resources & Links
-
Access the model on Hugging Face here: Model Card -
Explore our no-code UI demo on Hugging Face Spaces
-
See Examples of Prompts here on our Demo Page
Technical Deep Dive:
Blog Posts: