Instructions to use keras/moonshine_base_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- KerasHub
How to use keras/moonshine_base_en with KerasHub:
import keras_hub # Create a Seq2SeqLM model task = keras_hub.models.Seq2SeqLM.from_preset("hf://keras/moonshine_base_en")import keras_hub # Create a Backbone model unspecialized for any task backbone = keras_hub.models.Backbone.from_preset("hf://keras/moonshine_base_en") - Keras
How to use keras/moonshine_base_en 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://keras/moonshine_base_en") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from keras/moonshine_base_en: direct link, hf CLI and curl.
- Browser
- Download file 611 Bytes
-
https://huggingface.co/keras/moonshine_base_en/resolve/main/tokenizer.json
- Command line
-
hf download hf://keras/moonshine_base_en/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/keras/moonshine_base_en/resolve/main/tokenizer.json
611 Bytes
| { | |
| "module": "keras_hub.src.models.moonshine.moonshine_tokenizer", | |
| "class_name": "MoonshineTokenizer", | |
| "config": { | |
| "name": "moonshine_tokenizer", | |
| "trainable": true, | |
| "dtype": { | |
| "module": "keras", | |
| "class_name": "DTypePolicy", | |
| "config": { | |
| "name": "int32" | |
| }, | |
| "registered_name": null | |
| }, | |
| "config_file": "tokenizer.json", | |
| "proto": null, | |
| "sequence_length": null, | |
| "add_bos": false, | |
| "add_eos": false | |
| }, | |
| "registered_name": "keras_hub>MoonshineTokenizer" | |
| } |