Instructions to use zeromodels/whisper_tiny with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/whisper_tiny with ZeroModels:
# pip install -U zeromodels # ZeroModels is pure Keras 3, so pick a backend: "jax", "torch" or "tensorflow". import os os.environ["KERAS_BACKEND"] = "jax" from zeromodels import AutoZModel # AutoZModel reads the repo's model_type and loads the matching class. # For a task head use the matching loader, e.g. AutoZMImageClassify / AutoZMDetect / # AutoZMSemanticSegment / AutoZMTextGenerate (see zeromodels.auto). model = AutoZModel.from_weights("zeromodels/whisper_tiny") - Keras
How to use zeromodels/whisper_tiny with Keras:
# !pip install -U keras tensorflow huggingface_hub # Keras needs TensorFlow installed to read "hf://" paths, so the tensorflow backend is selected here; # "jax" and "torch" also work for computation once TensorFlow is installed. import os os.environ["KERAS_BACKEND"] = "tensorflow" import keras model = keras.saving.load_model("hf://zeromodels/whisper_tiny") - Notebooks
- Google Colab
- Kaggle
Download model.weights.h5 from zeromodels/whisper_tiny: direct link, hf CLI and curl.
- Browser
- Download file 151 MB
-
https://huggingface.co/zeromodels/whisper_tiny/resolve/main/model.weights.h5
- Command line
-
hf download hf://zeromodels/whisper_tiny/model.weights.h5
-
curl -L -o model.weights.h5 https://huggingface.co/zeromodels/whisper_tiny/resolve/main/model.weights.h5
151 MB
- Xet hash:
- b5114a4cc790376e0e8e503d1277b451d79ab7b6830ad63361d68c0a46150aec
- Size of remote file:
- 151 MB
- SHA256:
- 5271cce068b180b7160c390edd1a9ad94e5c05400f79912a20663bb8f464ef6b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.