Duplicated from ibm-granite/granite-4.0-1b-speech
How to use aoiandroid/granite-4.0-1b-speech with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="aoiandroid/granite-4.0-1b-speech")
# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("aoiandroid/granite-4.0-1b-speech") model = AutoModelForMultimodalLM.from_pretrained("aoiandroid/granite-4.0-1b-speech", device_map="auto")
https://huggingface.co/aoiandroid/granite-4.0-1b-speech/resolve/main/tokenizer.json
hf download hf://aoiandroid/granite-4.0-1b-speech/tokenizer.json
curl -L -o tokenizer.json https://huggingface.co/aoiandroid/granite-4.0-1b-speech/resolve/main/tokenizer.json
