Added HumAwareVAD to VAD Gallery (#194)

This commit is contained in:
Sourabh
2025-03-21 00:11:39 +05:30
committed by GitHub
parent 3fc441a6f0
commit ea36257abf

View File

@@ -45,6 +45,37 @@ document.querySelectorAll('.tag-button').forEach(button => {
<div class="grid cards" markdown>
- :speaking_head:{ .lg .middle }:eyes:{ .lg .middle } __HumAware VAD__
{: data-tags="vad-models"}
---
Description
**HumAware-VAD** is a fine-tuned version of **Silero-VAD**, specifically trained to **distinguish humming from actual speech**.
Standard VAD models often misclassify humming as speech, leading to inaccurate speech segmentation.
**HumAware-VAD** improves detection accuracy in environments with background humming, music, and vocal sounds.
**Install Instructions**
```sh
pip install humaware-vad
```
**Use with FastRTC**
```sh
git clone https://github.com/CuriousMonkey7/HumAwareVad.git
cd HumAwareVad
python app.py
```
<video width=98% src="https://github.com/user-attachments/assets/ea06a06f-d9e8-4203-a982-56326d160c9e" controls style="text-align: center"></video>
[:octicons-arrow-right-24: Demo](https://github.com/CuriousMonkey7/HumAwareVad/blob/main/app.py)
[:octicons-code-16: Repository](https://github.com/CuriousMonkey7/HumAwareVad/blob/main/humaware_vad/__init__.py)
</div>
<div class="grid cards" markdown>
- :speaking_head:{ .lg .middle }:eyes:{ .lg .middle } __Walkie Talkie__
{: data-tags="turn-taking-algorithm"}
@@ -141,4 +172,4 @@ In this gallery, you can find a collection of turn-taking algorithms and VAD mod
3. Open a [PR](https://github.com/freddyaboulton/fastrtc/edit/main/docs/turn_taking_gallery.md) to add your model to the gallery! Ideally you model package should be pip installable so other can try it out easily.
!!! tip "Package Naming Convention"
It is recommended to name your package `fastrtc-<package-name>` so developers can easily find it on [pypi](https://pypi.org/search/?q=fastrtc-).
It is recommended to name your package `fastrtc-<package-name>` so developers can easily find it on [pypi](https://pypi.org/search/?q=fastrtc-).