How to use stepfun-ai/Step-Audio-2-mini with Transformers:
# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("stepfun-ai/Step-Audio-2-mini", trust_remote_code=True, dtype="auto")
Hi,what is the minimum hardware required to run this model smoothly. The most important feature I need to test is real time speech conversation.
· Sign up or log in to comment