ZHU PEIYAN
ZHU PEIYAN
CLI is using only 1 cpu core too.
> 所有问题看这里就可以解决了，折腾了好久总结出来的：https://blog.opendeveloper.cn/yapi > > 修复bug汇总：https://blog.opendeveloper.cn/yapi/bug 请问一下，你的现成的docker镜像貌似是1.11.0，没有1.12.0，而你仓库里面的Dockerfile貌似也不是1.12.0?
> 我基于yapi的master分支改的代码，是1.11.0，其实就是最新版本的代码，跟1.12.0没区别 好的，明白了，谢谢
我用5，没啥问题
Any news?
> After looking at how `WITH_ACCELERATE` and devices are implemented in CTranslate2 itself, it seems that enabling MPS allows the "cpu" device backend to use MPS accleration, you can't use...
I found the diarization function also need to be changed to support MPS, in transcribe.py, change the following code `diarize_model = DiarizationPipeline(use_auth_token=hf_token, device=device)` to `diarize_model = DiarizationPipeline(use_auth_token=hf_token, device='mps')`
> Was anyone able to run it on mac? @colin4k with your latest comment on changing the diarization fuction, were you able to make it work? I can run it...
> Was anyone able to run it on mac? @colin4k with your latest comment on changing the diarization fuction, were you able to make it work? And after I changed...
> 可以使用中转的API嘛？不使用apenai官方的API？ 可以，修改openai_gpt.py `self.client = OpenAI(api_key=cfg['openai_api_key'],base_url=cfg['base_url'])` 然后在config.yaml中增加： ``` translator: type: openai openai_api_key: 'sk-xxx' base_url: 'http://xxx.xxx/v1' ```