Feature Extraction
Transformers
audio
speech
sparse-autoencoder
sae
interpretability
mechanistic-interpretability
hubert
Instructions to use Egorgij21/Audio-SAE-HuBERT-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Egorgij21/Audio-SAE-HuBERT-base with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="Egorgij21/Audio-SAE-HuBERT-base")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Egorgij21/Audio-SAE-HuBERT-base", dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 44ad3b8755b2fb9f6adc0ef27d58c0364ef0b7f36159f6bb42b1211f522f9950
- Size of remote file:
- 37.8 MB
- SHA256:
- a030b00b4a1c94e35696fd08fc1a49e84b2077f2ffb9fa382922cf4e2be6d789
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.