Instructions to use ibm-granite/granite-speech-3.3-2b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ibm-granite/granite-speech-3.3-2b with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="ibm-granite/granite-speech-3.3-2b")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("ibm-granite/granite-speech-3.3-2b") model = AutoModelForSpeechSeq2Seq.from_pretrained("ibm-granite/granite-speech-3.3-2b") - Notebooks
- Google Colab
- Kaggle
Is there any plan for publishing the training code?
#7
by mojtaba-nafez - opened
Hello,
Thank you for your great work on this project. I was wondering if there is any plan to publish the training code for this model? It would be very helpful for the community.
Best regards!
Hi, thank you for the kind words. We are going to publish a finetuning recipe soon, I hope it will suit your needs.
Hi @mojtaba-nafez
Thanks for your interest in our work.
Following your request, I wrote a minimal finetuning script.
Have a look at this pull request: https://github.com/huggingface/cookbook/pull/307
Once the PR is merged, we'll add it to the docs.