Instructions to use ibm-granite/granite-speech-4.1-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-4.1-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-4.1-2b")# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("ibm-granite/granite-speech-4.1-2b") model = AutoModelForMultimodalLM.from_pretrained("ibm-granite/granite-speech-4.1-2b", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- AMD Developer Cloud
ONNX versions created:
#7
by smcleod - opened
Hello, just letting you know that I've created ONNX versions of the 3 Granite Speech 4.1 2b models in case anyone wants them.
- https://huggingface.co/smcleod/ibm-granite-speech-4.1-2b-onnx
- https://huggingface.co/smcleod/ibm-granite-speech-4.1-2b-plus-onnx
- https://huggingface.co/smcleod/ibm-granite-speech-4.1-2b-nar-onnx
These took a bit for me to get my head around and I burned a lot of Opus tokens in the process, so if anyone finds any issues with them, please do let me know, otherwise enjoy!