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

Added model download technique #12

Closed hp2413 closed 2 months ago

hp2413 commented 2 months ago

With this single scrip to download both the fine tuned Llama-3.1-8B-Omni mode and Whisper-large-v3 model will make the setup process more easier, and also solve few ambiguities.