From 623a4860566cc0242c09c9d08adecaef2efaeff7 Mon Sep 17 00:00:00 2001 From: Georgi Gerganov Date: Wed, 23 Nov 2022 09:52:36 +0200 Subject: [PATCH] Update README.md --- README.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/README.md b/README.md index 003674a..a9e621b 100644 --- a/README.md +++ b/README.md @@ -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))