How would we use the pretrained model in our own python code?

ictnlp / LLaMA-Omni

LLaMA-Omni is a low-latency and high-quality end-to-end speech interaction model built upon Llama-3.1-8B-Instruct, aiming to achieve speech capabilities at the GPT-4o level.

https://arxiv.org/abs/2409.06666

Apache License 2.0

2.62k stars 177 forks source link

How would we use the pretrained model in our own python code? #7

Closed PhilipAmadasun closed 2 months ago

PhilipAmadasun commented 2 months ago

How would we use the pretrained model in our own python code instead if CLI. Could you please share some examples.

Poeroz commented 2 months ago

Hello, you can refer to the infer.py to load the model in Python and use model.generate() for inference.