Instructions to use algorithco/whisper-large-v3-turbo with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use algorithco/whisper-large-v3-turbo with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="algorithco/whisper-large-v3-turbo")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("algorithco/whisper-large-v3-turbo") model = AutoModelForSpeechSeq2Seq.from_pretrained("algorithco/whisper-large-v3-turbo", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit History
-
Add sherpa-onnx int8 runtime files for offline desktop inference
Verified signatureAdditive only: turbo encoder/decoder int8 ONNX + tokens. Existing weights untouched. Source: csukuangfj/sherpa-onnx-whisper-turbo.b90e848
-
Duplicate from openai/whisper-large-v3-turbo
Co-authored-by: Yoach Lacombe <ylacombe@users.noreply.huggingface.co>5937080