thewintersun
thewintersun
when to add the sequence-discriminative training to eesen? for example,: sMBR.
自从有一次UI做了比较大的改动的那个版本之后, 后来实时请求的基本上就没有成功过。 但是用老的版本一直都是可以用的。 log如下: ### 错误描述 To create a public link, set `share=True` in `launch()`. 2023-03-18 22:41:30,250 [INFO] [utils.py:311] 输入为:112 2023-03-18 22:41:30,259 [INFO] [utils.py:340] 使用流式传输 2023-03-18 22:41:30,259 [INFO] [utils.py:164] 实时回答模式...
--load_8bit True 会出来这个错误, 如果False就不会有错误,但是结果是乱码。 Traceback (most recent call last): File "/home/jovyan/dluo/github/LaWGPT/webui.py", line 211, in fire.Fire(main) File "/home/jovyan/.conda/envs/lawgpt/lib/python3.10/site-packages/fire/core.py", line 141, in Fire component_trace = _Fire(component, args, parsed_flag_args, context, name) File "/home/jovyan/.conda/envs/lawgpt/lib/python3.10/site-packages/fire/core.py",...