Instructions to use openai/whisper-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use openai/whisper-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="openai/whisper-large")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("openai/whisper-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("openai/whisper-large") - Notebooks
- Google Colab
- Kaggle
How to Generate a .mlmodel File for Apple's CoreML Framework
I am exploring the possibilities of using advanced machine learning models, like OpenAI's Whisper large model, in iOS and macOS applications. However, I'm facing a challenge as there are no readily available .mlmodel files that suit my needs. Could anyone guide me on how to generate a .mlmodel file from scratch or convert existing models to be compatible with Apple's CoreML framework? Specifically, I'm interested in steps, tools, or libraries necessary for this conversion process. Additionally, any tips on optimizing these models for better performance on Apple devices would be greatly appreciated. I am looking for advice from those who have experience in this area or know relevant resources. Thank you!