Instructions to use AmimulBmeIU/asl-alphabet-classifier with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Keras
How to use AmimulBmeIU/asl-alphabet-classifier with Keras:
# Available backend options are: "jax", "torch", "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" import keras model = keras.saving.load_model("hf://AmimulBmeIU/asl-alphabet-classifier") - Notebooks
- Google Colab
- Kaggle
ASL Alphabet Classifier
Classifies static ASL fingerspelling letters (A-Y, excluding J and Z) from 21 MediaPipe hand landmarks (x, y, z).
Pipeline
Camera -> MediaPipe Hand Landmarker -> 21 landmarks -> this model -> predicted letter -> text -> Web Speech API / gTTS -> voice output.
Files
model.keras: trained Keras modellabels.json: ordered list mapping output index -> lettertfjs/: browser-ready TensorFlow.js version of the same model
Validation accuracy: 0.9415
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support