Instructions to use zeromodels/whisper_base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- ZeroModels
How to use zeromodels/whisper_base 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_base") - Keras
How to use zeromodels/whisper_base 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_base") - Notebooks
- Google Colab
- Kaggle
File size: 302 Bytes
605a420 2bc85ad | 1 2 3 4 5 6 7 8 9 10 11 12 | {
"library_name": "zeromodels",
"zeromodels_version": "1.1.3",
"preprocessor_module": "zeromodels.models.whisper",
"preprocessor_class": "WhisperFeatureExtractor",
"variant": "whisper_base",
"sampling_rate": 16000,
"n_fft": 400,
"hop_length": 160,
"n_mels": 80,
"chunk_length": 30
} |