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
2.61k stars 175 forks source link

about Gradio Demo #47

Open mysxs opened 1 month ago

mysxs commented 1 month ago

在复现Gradio Demo的时候遇到了一些问题,我已经启动了一个controller,然后在Launch a gradio web server时遇到问题,命令:python -m omni_speech.serve.gradio_web_server --controller http://localhost:10000 --port 8000 --model-list-mode reload --vocoder vocoder/g_00500000 --vocoder-cfg vocoder/config.json 错误:requests.exceptions.ConnectionError: SOCKSHTTPConnectionPool(host='localhost', port=10000): Max retries exceeded with url: /refresh_all_workers (Caused by NewConnectionError('<urllib3.contrib.socks.SOCKSConnection object at 0x7fe61ee1dfc0>: Failed to establish a new connection: [Errno 111] Connection refused')) 我把代理关了也不行,该怎么解决?