Instructions to use bosonai/higgs-audio-v2-tokenizer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bosonai/higgs-audio-v2-tokenizer with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="bosonai/higgs-audio-v2-tokenizer")# Load model directly from transformers import AutoFeatureExtractor, AutoModel extractor = AutoFeatureExtractor.from_pretrained("bosonai/higgs-audio-v2-tokenizer") model = AutoModel.from_pretrained("bosonai/higgs-audio-v2-tokenizer", device_map="auto") - Inference
- Notebooks
- Google Colab
- Kaggle
Uploaded higgs-audio-v2-generation-3B-base's model to this repo
#6
by grimavatar - opened
Just checking if this is intentional or a mistake?
Looks like a mistake. I don't know why we should download the LLM when we only need the tokenizer.