Upload folder using huggingface_hub

README.md

@@ -27,7 +27,10 @@ pipeline_tag: audio-classification
 
 thumbnail: https://huggingface.co/front/assets/huggingface_logo.svg
 ---
+## Resume
+Tiny audio classifier designed for environmental monitoring on ultra-low-power microcontrollers such as the Raspberry Pi Pico 2 W. The model classifies environmental sounds into six coarse classes and is optimized for TinyML deployment.
 
+## Specifications
 Task: bioacoustic coarse classification
 
 Classes: bird, human, motor, rain_wind, insect, animal
@@ -42,4 +45,12 @@ Test accuracy: 87.44 %
 
 Datasets: ESC-50, FSD50K, InsectSet32, filtered bird dataset
 
-Limitations: modèle expérimental, pas encore validé terrain
+Limitations: modèle expérimental, pas encore validé terrain
+
+## Usage
+
+```py
+import tensorflow as tf
+
+model = tf.keras.models.load_model("ecopulse_cnn.keras")
+```