Update README.md

This commit is contained in:
Georgi Gerganov 2022-11-23 09:52:36 +02:00 committed by GitHub
parent 2f596f5b33
commit 623a486056
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23

View File

@ -30,10 +30,14 @@ The entire implementation of the model is contained in 2 source files:
- Transformer inference: [whisper.h](whisper.h) / [whisper.cpp](whisper.cpp)
Having such a lightweight implementation of the model allows to easily integrate it in different platforms and applications.
As an example, here is a video of running the model on an iPhone 13 device - fully offline, on-device:
As an example, here is a video of running the model on an iPhone 13 device - fully offline, on-device: [whisper.objc](https://github.com/ggerganov/whisper.cpp/tree/master/examples/whisper.objc)
https://user-images.githubusercontent.com/1991296/197385372-962a6dea-bca1-4d50-bf96-1d8c27b98c81.mp4
Or you can even run it in the straigt in your browser: [talk.wasm](https://github.com/ggerganov/whisper.cpp/tree/master/examples/talk.wasm)
https://user-images.githubusercontent.com/1991296/203411580-fedb4839-05e4-4474-8364-aaf1e9a9b615.mp4
## Implementation details
- The core tensor operations are implemented in C ([ggml.h](ggml.h) / [ggml.c](ggml.c))