xiao jie comments

Results 10 comments of


                                            xiao jie

Why is the streaming parameter of the TTS interface set to True, which actually returns all fragments instead of streaming

In that case, wouldn't it be a fake stream? If we stream the file output, the response will be greatly improved

Why is the streaming parameter of the TTS interface set to True, which actually returns all fragments instead of streaming

I did the same thing, splitting sentences and cloning in batches, but I am working on a low latency real-time interaction example. If I could do true streaming, the experience...

Why is the streaming parameter of the TTS interface set to True, which actually returns all fragments instead of streaming

Sorry, according to my understanding, your approach in this paragraph is to split the sentence and gradually call TTS in batches to create a "fake stream". However, what I want...

可以麻烦支持一下Azure的openAI吗

如何在页面配置呢?我已经正确填写了我的url 以及key以及gpt4o

可以麻烦支持一下Azure的openAI吗

404等等，页面并没有让我填version,deployment这些的信息项

可以麻烦支持一下Azure的openAI吗

> > 404等等，页面并没有让我填version,deployment这些的信息项 > > 我尝试注册了一下 azure，提示没有配额，需要申请资源才可以用。建议如果您有代码功底可以帮我们适配一下你方便直接告诉我链接模型的代码大概在哪个地方么

[Bug] ModuleNotFoundError: No module named 'mmengine'

May I ask if you have solved it? I have also encountered a similar problem

请问魔搭部署之后,怎么样在UI-TARS-desktop客户端中调用,客户端的VLM Provider中只有 vLLM和Hugging Face,另外求UI-TARS相关的群

我也一样没有反应，有解决了嘛

Deploying with Docker and using a proxy openai address cannot use this model and will result in nginx errors

![Image](https://github.com/user-attachments/assets/c82217df-5792-4376-a147-9b738a1b98e9)

Deploying with Docker and using a proxy openai address cannot use this model and will result in nginx errors

So should I directly modify the environment variables？[@dosu](https://go.dosu.dev/dosubot)