Tony

> I have met almost the same error, and I use tiktoken 0.3.1

And I use Macbook air M1.

Problems solved, refer to https://github.com/openai/tiktoken/issues/63#issuecomment-1469536106. Have to delete the cached files inside this cache folder.

> you might wanna use the reconnect option as well incase of partial downloads, for example this: `wget -c https://dl.suno-models.io/bark/models/v0/text_2.pt -O ~/.cache/suno/bark_v0/54afa89d65e318d4f5f80e8e8799026a.pt` Do I have to change the model name...

> > > you might wanna use the reconnect option as well incase of partial downloads, for example this: `wget -c https://dl.suno-models.io/bark/models/v0/text_2.pt -O ~/.cache/suno/bark_v0/54afa89d65e318d4f5f80e8e8799026a.pt` > > > > > >...

> these should be all the current models needed: > > ``` > # download small models > wget -c https://dl.suno-models.io/bark/models/v0/text.pt -O ~/.cache/suno/bark_v0/41a4361a0bb21b667a35fbf76a309a77.pt > wget -c https://dl.suno-models.io/bark/models/v0/coarse.pt -O ~/.cache/suno/bark_v0/db7988c269f58606a4b3a3d3497c6b95.pt >...

With a api key configurable, and choose from a list of available voices.

bob有个问题是，收藏的有的是单词，更多的是对句子的翻译。所以收藏列表就会略显的乱。 现在我用自己包的popclip插件来使用aivoc，唯一的问题是需要我开着iterm，每次popclip选择一个句子后，需要在iterm中先激活venv环境，再去翻译。虽然也都在后台，不过不适合非技术受众。 其实现在的翻译的软件很多，各种软件都可以一行代码调用chatgpt来翻译，但是生词本管理上做的还不够，感觉可以就生词本这一个单点做更多优化。上游接受bob和欧路词典等翻译软件的数据导出，下游传递到划词复习的手机app，此外，可以做一下找AI编出的故事的持久化，或者让故事情节保持连续，形成有动力持续回顾的内容。

期望这个功能能上，我也想看更早的文章

这个可以配置reality吗？