extern/whisper.cpp
1
0
Fork 1
mirror of https://github.com/ggerganov/whisper.cpp.git synced 2025-06-30 06:20:07 +02:00
Code Issues Packages Projects Releases Wiki Activity

talk.wasm : refactoring + update README.md

Browse Source
This commit is contained in:
Georgi Gerganov
2022-11-24 00:08:57 +02:00
parent 00f46dbc1d
commit be3b720f96
7 changed files with 988 additions and 1046 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
examples/talk.wasm/README.md
View File

@ -16,7 +16,13 @@ This demo leverages 2 modern neural network models to create a high-quality voic
The web page does the processing locally on your machine. The processing of these heavy neural network models in the
browser is possible by implementing them efficiently in C/C++ and using the browser's WebAssembly SIMD capabilities for
extra performance. For more detailed information, checkout the [current repository](https://github.com/ggerganov/whisper.cpp).
extra performance:
- The Whisper C++ implementation is here: [whisper.h](/whisper.h) / [whisper.cpp](/whisper.cpp)
- The GPT-2 C++ implementation is here: [gpt-2.h](gpt-2.h) / [gpt-2.cpp](gpt-2.cpp)
- Both models use a custom tensor library implemented in C: [ggml.h](/ggml.h) / [ggml.c](/ggml.c)
- The HTML/JS layer is here: [index-tmpl.html](index-tmpl.html)
- The Emscripten bridge between C/C++ and JS is here: [emscripten.cpp](emscripten.cpp)
In order to run the models, the web page first needs to download the model data which is about ~350 MB. The model data
is then cached in your browser's cache and can be reused in future visits without downloading it again.
@ -33,11 +39,11 @@ In order to run this demo efficiently, you need to have the following:
Notice that this demo is using the smallest GPT-2 model, so the generated text responses are not always very good.
Also, the prompting strategy can likely be improved to achieve better results.
The demo is quite computationally heavy - it's not usual to run these transformer models in a browser. Typically, they
run on powerful GPU hardware. So for better experience, you do need to have a powerful computer.
The demo is quite computationally heavy, so you need a fast CPU. It's not usual to run these transformer models in a
browser. Typically, they run on powerful GPUs.
Probably in the near future, mobile browsers will start supporting WASM SIMD. This will allow to run the demo on your
phone or tablet. But for now this functionality is not supported on mobile devices (at least not on iPhone).
Currently, mobile browsers do not support the Fixed-width SIMD WebAssembly capability, so you cannot run this demo
on a phone or a tablet. Hopefully, in the near future this will become supported.
## Todo