From c838a2a24bc0f6c06c69044d074e15480fcf5596 Mon Sep 17 00:00:00 2001 From: Konstantin Date: Mon, 16 Jan 2023 15:19:41 +0100 Subject: Another readme for the nuget package --- WhisperNet/Readme.md | 12 ++++++++++++ WhisperNet/WhisperNet.nuspec | 2 ++ 2 files changed, 14 insertions(+) create mode 100644 WhisperNet/Readme.md diff --git a/WhisperNet/Readme.md b/WhisperNet/Readme.md new file mode 100644 index 0000000..644384c --- /dev/null +++ b/WhisperNet/Readme.md @@ -0,0 +1,12 @@ +This library implements high-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model. + +The library requires a hardware GPU which supports Direct3D 11.0, a 64-bit Windows OS, only works within 64-bit processes, and requires a 64 bit CPU which supports SSE 4.1. + +The main entry point of the llibrary is `Whisper.Library` static class. +Call `loadModel` function from that class to load an ML model from a binary file. + +These binary files are available for free download on [Hugging Face]( https://huggingface.co/datasets/ggerganov/whisper.cpp). +I recommend `ggml-medium.bin` (1.42GB in size), because I’ve mostly tested the software with that model. + +Once the model is loaded, create a context by calling `createContext` extension method, +then use that object to transcribe or translate multimedia files or realtime audio captured from microphones. \ No newline at end of file diff --git a/WhisperNet/WhisperNet.nuspec b/WhisperNet/WhisperNet.nuspec index d0a61f7..f4f6cff 100644 --- a/WhisperNet/WhisperNet.nuspec +++ b/WhisperNet/WhisperNet.nuspec @@ -16,6 +16,7 @@ + docs/Readme.md @@ -23,5 +24,6 @@ + \ No newline at end of file -- cgit v1.2.3