DanielWu

from [Demo code](https://github.com/psharanda/Atributika/blob/03602383e9e046bb0ebab64de570096fb14d6267/Demo/Sources/Snippet.swift#L220) ``` func stringWithImage() -> NSAttributedString { let font = UIFont(name: "HelveticaNeue-BoldItalic", size: 12)! let b = Attrs().font(font).underlineStyle(.single) let img = TagTuner(style: { let style = Attrs() if...

请问现在 iOS 是不是仍然只能支持 cpu provider？我尝试使用 "coreml" provider 初始化模型，会遭遇崩溃。 @csukuangfj

> Could you re-export the model with batch size == 1 so that there are no dynamic shapes in the streaming model, and retry? 你说的这个要怎么做呢？我使用的模型是在这里当前仓库下载的，不是自己导出的模型 @csukuangfj https://github.com/k2-fsa/sherpa-onnx/releases/tag/tts-models 我选择了 https://github.com/k2-fsa/sherpa-onnx/releases/download/tts-models/vits-coqui-en-ljspeech-neon.tar.bz2

I also encountered the same issue, but fortunately, I found the cause and fixed it. The crash here is caused by a null pointer, SherpaOnnxOfflineTtsWrapper.tts == nil, which is due...