whisper.cpp
whisper.cpp copied to clipboard
Port of OpenAI's Whisper model in C/C++
`leyer` → `layer` `timestanps` → `timestamps`
Hi - awesome work! I am wondering if there is a size or duration limit to the size of file that can be processed using this library?
I see that WebAssembly isn't supported with React JS According to some articles - https://www.telerik.com/blogs/using-webassembly-with-react - we can use - react-app-rewired and wasm-loader , but these need to be call...
How can I use the 4 bit models with the main example? My computer has less RAM and has problem loading the original Large model and thus trying to use...
I was able to integrate the coreml model in the app and the log says, "Core ML Model Loaded" (please see the attached screenshot for reference) but when I am...
would allow to link dynamically to whisper in an easy way
I've tried to convert `small` model to CoreML format on Mac M1 by following the CoreML instruction. However, the process stuck after `Running MIL backend_mlprogram pipeline` step. I can see...
Followed instruction in README to convert coreml model. Then tested on macOS, it works perfectly. Then copy the model to SwiftUI example project, followed by adding WHISPER_USE_COREML processor and coreml...
### Question When I execute multiple cores and threads, even though the number of cores is set to be less than the number of cores on the machine, the program...
Well, it uses **50% less power** - that's "double" performance. Basically, instead of using spinlocks, I made `whisper.cpp` use condition variables with mutices (mutex plural?). Whisper is not really a...