Hugging Face's logo

sukriramli
/
tiny-bird-diffusion

Audio Classification
PyTorch
Joblib
English
bioacoustics
bird-sound-identification
vision-transformers
protoclr
umap
hdbscan
Model card Files
xet
 Community
sukriramli commited on
Commit
c292b26
·
verified ·
1 Parent(s): e33bdc0

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +4 -4
README.md CHANGED
@@ -19,13 +19,13 @@ metrics:
19
 
20
  # 🦅 Edge-Optimized Bioacoustic Atlas & Real-Time Avian Classifier
21
 
22
- [%F0%9F%93%93%20Open%20In%20Colab](https://colab.research.google.com/drive/1EL5VS_vAKvojPf5UPuQVFbK5gkgP51hB?usp=sharing)
23
- [![]_blue)](https://colab.research.google.com/drive/1EL5VS_vAKvojPf5UPuQVFbK5gkgP51hB?usp=sharing)
24
  [![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-ee4c2c?logo=pytorch)](https://pytorch.org/)
25
  [![Optimization: UMAP + HDBSCAN](https://img.shields.io/badge/Optimization-UMAP%20%2B%20HDBSCAN-green)]()
26
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
27
 
28
- A decoupled, ultra-lightweight machine learning pipeline designed for low-latency edge deployment, automated avian species tracking, and interactive audio streaming.
29
 
30
  By leveraging **Prototypical Contrastive Learning (ProtoCLR)** backbones combined with advanced topological manifold compression (**UMAP & HDBSCAN**), this system projects complex audio waveforms onto a dense, 2D geometric map. The resulting production architecture handles **168 unique biological species** across **149 autonomous eco-acoustic clusters** natively in a client browser window with sub-second latency—completely bypassing the need for compute-heavy cloud inferencing heads.
31
 
@@ -52,4 +52,4 @@ Pre-trained foundation models are typically trained on pristine, studio-grade wi
52
 
53
  * `augment.py`: Digital Signal Processing (DSP) environment warping functions (Noise, Echo, Muffling filters).
54
  * `pipeline.py`: Low-latency engineering pipeline managing model configuration and UMAP coordinate projection.
55
- * `api.py`: Clean, production-ready prediction endpoint designed for real-time app integration.
 
19
 
20
  # 🦅 Edge-Optimized Bioacoustic Atlas & Real-Time Avian Classifier
21
 
22
+ [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1EL5VS_vAKvojPf5UPuQVFbK5gkgP51hB?usp=sharing)
23
+ [![Hugging Face Repository](https://img.shields.io/badge/%F0%9F%A4%97%20Hugging%20Face-Repository-blue)](https://huggingface.co/sukriramli/tiny-bird-diffusion)
24
  [![Framework: PyTorch](https://img.shields.io/badge/Framework-PyTorch-ee4c2c?logo=pytorch)](https://pytorch.org/)
25
  [![Optimization: UMAP + HDBSCAN](https://img.shields.io/badge/Optimization-UMAP%20%2B%20HDBSCAN-green)]()
26
  [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](https://opensource.org/licenses/MIT)
27
 
28
+ A decoupled, ultra-lightweight machine learning pipeline designed for low-latency edge deployment, automated avian species tracking, and interactive audio streaming.
29
 
30
  By leveraging **Prototypical Contrastive Learning (ProtoCLR)** backbones combined with advanced topological manifold compression (**UMAP & HDBSCAN**), this system projects complex audio waveforms onto a dense, 2D geometric map. The resulting production architecture handles **168 unique biological species** across **149 autonomous eco-acoustic clusters** natively in a client browser window with sub-second latency—completely bypassing the need for compute-heavy cloud inferencing heads.
31
 
 
52
 
53
  * `augment.py`: Digital Signal Processing (DSP) environment warping functions (Noise, Echo, Muffling filters).
54
  * `pipeline.py`: Low-latency engineering pipeline managing model configuration and UMAP coordinate projection.
55
+ * `api.py`: Clean, production-ready prediction endpoint designed for real-time app integration.