Feature Extraction
Transformers
Safetensors
wav2vec2
pretraining
bioacoustics
audio
self-supervised-learning
dolphin
bottlenose-dolphin
whistle
openwhistle
Instructions to use dolphinteam/OpenWhistle-BioClust with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dolphinteam/OpenWhistle-BioClust with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="dolphinteam/OpenWhistle-BioClust")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("dolphinteam/OpenWhistle-BioClust") model = AutoModelForPreTraining.from_pretrained("dolphinteam/OpenWhistle-BioClust", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
8 days ago
-
Publish OpenWhistle-BioClust Fairseq Wav2Vec2 trained for 400,000 updates
Verified signatureFinal checkpoint exported with strict tensor mapping and verified Fairseq/Transformers embedding parity. Includes model configuration, audio feature extractor, native training metrics, model card and reproducibility metadata.3f64f7b