Instructions to use primeline/whisper-large-v3-german with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use primeline/whisper-large-v3-german with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="primeline/whisper-large-v3-german")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("primeline/whisper-large-v3-german") model = AutoModelForMultimodalLM.from_pretrained("primeline/whisper-large-v3-german") - Notebooks
- Google Colab
- Kaggle
Best model for German transcription! - Serverless api?
From my experience, this is currently the best model for German transcription. Amazing work! π
Does anyone know of a model that can compete with this?
I'd also love to know if there's any chance of making this available via the Serverless API. I can't be the only one who needs high-quality German transcription, and this model is simply the best option out there. Waiting for a dedicated endpoint to spin up β or paying for a T4 around the clock β isn't really a practical alternative.
Best,
Tim
Hi Tim,
We can offer this in our Datacenter
https://partimus.com/en/services/ai-consulting/
Just hit us up with your requirements and we will find a Solution for you.
Cheers,
Marius from primeline/partimus