# Latest

**URL:** https://earthspeciesproject.discourse.group/latest.md

[Latest](https://earthspeciesproject.discourse.group/latest.md) · [Categories](https://earthspeciesproject.discourse.group/categories.md) · [Tags](https://earthspeciesproject.discourse.group/tags.md)

---

## [Welcome to Earth Species Project! 👋](https://earthspeciesproject.discourse.group/t/welcome-to-earth-species-project/5)

<div class="topic-metadata">

**Author:** [@system](https://earthspeciesproject.discourse.group/u/system)\
**Replies:** 0\
**Last updated:** [July 23, 2025, 8:08pm UTC](https://earthspeciesproject.discourse.group/t/welcome-to-earth-species-project/5 "2025-07-23T20:08:38Z")

</div>

We are so glad you joined us. Here are some things you can do to get started: :speaking\_head: Introduce yourself by adding your picture and information about yourself and your interests to your profile. What is one thi…

---

## [How to build a dog behavior app with NatureLM-audio](https://earthspeciesproject.discourse.group/t/how-to-build-a-dog-behavior-app-with-naturelm-audio/21)

<div class="topic-metadata">

**Author:** [@svs](https://earthspeciesproject.discourse.group/u/svs)\
**Replies:** 3\
**Last updated:** [September 20, 2026, 3:40pm UTC](https://earthspeciesproject.discourse.group/t/how-to-build-a-dog-behavior-app-with-naturelm-audio/21 "2026-09-20T15:40:11Z")

</div>

Hi ESP team, I tested NatureLM-audio using the sample voices in the demo and it honestly made me even more curious. I’m a consumer product builder, and I’m exploring how to build something that helps everyday people und…

---

## [Evaluating NatureLM-audio Over Windows](https://earthspeciesproject.discourse.group/t/evaluating-naturelm-audio-over-windows/20)

<div class="topic-metadata">

**Author:** [@CarterWebb](https://earthspeciesproject.discourse.group/u/CarterWebb)\
**Replies:** 1\
**Last updated:** [March 17, 2026, 5:45pm UTC](https://earthspeciesproject.discourse.group/t/evaluating-naturelm-audio-over-windows/20 "2026-03-17T17:45:45Z")

</div>

Hi all, I have been experimenting with using NatureLM-audio/BEANS-Zero for call-type classification on the xeno-canto dataset like is detailed in the paper. I have successfully performed the zero-shot call-type classific…

---

## [AniMUL: NatureLM dataset + Qwen3-Omni](https://earthspeciesproject.discourse.group/t/animul-naturelm-dataset-qwen3-omni/19)

<div class="topic-metadata">

**Author:** [@jebba](https://earthspeciesproject.discourse.group/u/jebba)\
**Replies:** 1\
**Last updated:** [October 10, 2025, 9:22pm UTC](https://earthspeciesproject.discourse.group/t/animul-naturelm-dataset-qwen3-omni/19 "2025-10-10T21:22:38Z")

</div>

I am working on a project to create a new model using the NatureLM dataset and the Qwen3-Omni model. When it was released, I tested the ESP NatureLM-audio model, which is based on Llama 3.1. While that latter model is…

---

## [Feedback for NatureLM-audio UI: Hugging Face Spaces Demo](https://earthspeciesproject.discourse.group/t/feedback-for-naturelm-audio-ui-hugging-face-spaces-demo/17)

<div class="topic-metadata">

**Author:** [@diane](https://earthspeciesproject.discourse.group/u/diane)\
**Replies:** 2\
**Last updated:** [September 23, 2025, 6:49am UTC](https://earthspeciesproject.discourse.group/t/feedback-for-naturelm-audio-ui-hugging-face-spaces-demo/17 "2025-09-23T06:49:01Z")

</div>

We just released our first demo of NatureLM-audio on :hugs: Hugging Face Spaces! :backhand\_index\_pointing\_right: Try out the demo :open\_book: Read our step-by-step tutorial This is the main thread for sharing feedback,…