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 data and evaluation data
#4
by ElectronicFoobar - opened
Hi,
Which parameters did you use for training?
Also, can you shed light on which data you used for training and which data you evaluated on (to get the WER of 5.8)?