Erik Hermansen

If my app is listening for specific words like "four", I usually write logic to catch homonyms, e.g., "for". So basically, someplace I'm going to have code that is like...

Which line of the code throws the exception? I'm guessing `Vosk.createModel()` but it would be nice to confirm.

Realizing now I'm replying to a stale message. Did you get past the problem?

(I'm not a maintainer) > Does WebLLM work based on the principle of running LLMs locally on a computer? Sorta. It runs LLMs in the browser (not native). Charlie Ruan...

> local model ala ollama would be significantly faster than their web counter part. so the algo would be: if ollama is present, use ollama else use webgpu Yeah, that's...

Check your HTTP requests in the browser (Network tab in Developer Tools on Chrome). I'm guessing you've got a 404 on one of the model requests. If that's the case,...

I won't speak for the WebLLM project. I have an interest in adding a feature like this to my separate project (https://github.com/DecentAppsNet) which wraps web-llm. Feel free to contact me...

Not ideal, @kentcdodds , but as a workaround, you can parse the [xx/yy] from the text. See the `_findPercentCompleteFromStatus()` function at top of https://github.com/DecentAppsNet/decentapp-template/blob/main/src/loadScreen/interactions/initialization.ts

I would favor an asynchronous version of `interruptGenerate()` that returns after the engine is ready to receive a new generation request. The current implementation sets a signal flag and returns...

Are you trying to build from source or just importing the package? Yes, you'll need WASM. But if you are importing it should already be included. I can't remember if...