Instructions to use nyrahealth/CrisperWhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyrahealth/CrisperWhisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nyrahealth/CrisperWhisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nyrahealth/CrisperWhisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("nyrahealth/CrisperWhisper") - Notebooks
- Google Colab
- Kaggle
Onnx version?
#4
by hammeiam - opened
I would love to use this model in a browser environment. @Xenova has been doing some amazing work on transformers.js and compiling models with Onnx (example here https://huggingface.co/onnx-community/whisper-base_timestamped).
Could you do something similar for this model?
not sure about the conversion flow....i hope someone else more familiar with transformers.js and ONNX is willing to help you here or you manage to figure it out yourself :)