dotnet add package WhisperNet --version 1.12.0
NuGet\Install-Package WhisperNet -Version 1.12.0
<PackageReference Include="WhisperNet" Version="1.12.0" />
paket add WhisperNet --version 1.12.0
#r "nuget: WhisperNet, 1.12.0"
// Install WhisperNet as a Cake Addin #addin nuget:?package=WhisperNet&version=1.12.0 // Install WhisperNet as a Cake Tool #tool nuget:?package=WhisperNet&version=1.12.0
This library implements high-performance GPGPU inference of OpenAI's Whisper automatic speech recognition (ASR) model.
The main entry point of the llibrary is
Whisper.Library static class.
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.
ggml-medium.bin (1.42GB in size, but that web page says 1.53 GB), because I’ve mostly tested the software with that model.
Compressed models in ZIP format with
mlmodelc in the file name are not supported.
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.
|Product||Versions Compatible and additional computed target framework versions.|
|.NET||net6.0 is compatible. net6.0-android was computed. net6.0-ios was computed. net6.0-maccatalyst was computed. net6.0-macos was computed. net6.0-tvos was computed. net6.0-windows was computed. net7.0 was computed. net7.0-android was computed. net7.0-ios was computed. net7.0-maccatalyst was computed. net7.0-macos was computed. net7.0-tvos was computed. net7.0-windows was computed. net8.0 was computed. net8.0-android was computed. net8.0-ios was computed. net8.0-maccatalyst was computed. net8.0-macos was computed. net8.0-tvos was computed. net8.0-windows was computed.|
- ComLightInterop (>= 1.3.7)
This package is not used by any NuGet packages.
This package is not used by any popular GitHub repositories.
Updated models source URL in the documentation.
Reliability enhancement, microphone capture less likely to transition to “Stalled” state and discard the audio.