Instructions to use mhenrichsen/hviske with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mhenrichsen/hviske with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="mhenrichsen/hviske")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("mhenrichsen/hviske") model = AutoModelForSpeechSeq2Seq.from_pretrained("mhenrichsen/hviske") - Notebooks
- Google Colab
- Kaggle
Training parameters and training setup?
#3
by ymir95 - opened
I'm curious how you trained the model, did you use PEFT or similar?
What training parameters did you go with and what hardware?
Hi ymir.
The model is currently failing after being uploaded. It's currently retraining with new code. If that works (which I expect it will), I will share the code in this repo.
Fantastic!