Gravicode.MediaPipeNet.Tasks.Audio
1.0.0
dotnet add package Gravicode.MediaPipeNet.Tasks.Audio --version 1.0.0
NuGet\Install-Package Gravicode.MediaPipeNet.Tasks.Audio -Version 1.0.0
<PackageReference Include="Gravicode.MediaPipeNet.Tasks.Audio" Version="1.0.0" />
<PackageVersion Include="Gravicode.MediaPipeNet.Tasks.Audio" Version="1.0.0" />
<PackageReference Include="Gravicode.MediaPipeNet.Tasks.Audio" />
paket add Gravicode.MediaPipeNet.Tasks.Audio --version 1.0.0
#r "nuget: Gravicode.MediaPipeNet.Tasks.Audio, 1.0.0"
#:package Gravicode.MediaPipeNet.Tasks.Audio@1.0.0
#addin nuget:?package=Gravicode.MediaPipeNet.Tasks.Audio&version=1.0.0
#tool nuget:?package=Gravicode.MediaPipeNet.Tasks.Audio&version=1.0.0
Gravicode.MediaPipeNet.Tasks.Audio
Audio tasks of MediaPipe.NET, ported from Google MediaPipe Tasks and running on ONNX Runtime:
- AudioClassifier — YAMNet, 521 AudioSet classes per 0.975 s window (speech, music, animals, alarms, ...).
- VoiceActivityDetector — speech/non-speech frames and merged speech segments, built on YAMNet's speech classes.
Both support an audio-clips mode and an audio-stream mode (chunks of any size, callback per window).
AudioData loads WAV files (PCM 8/16/24/32-bit, float) and resamples to 16 kHz.
using MediaPipeNet.Tasks.Audio;
using var classifier = AudioClassifier.Create();
foreach (var window in classifier.Classify(AudioData.LoadWav("speech.wav")))
Console.WriteLine($"{window.TimestampMs} ms: {window.TopCategory}");
The YAMNet model comes from Gravicode.MediaPipeNet.Models.Audio (installed or downloaded on first use).
MediaPipe.NET — a native .NET 10 port of Google MediaPipe's tasks on ONNX Runtime.
Created by Gravicode Studios, led by Kang Fadhil. Library: Apache-2.0. Model weights: © Google LLC, Apache-2.0.
Documentation (English & Bahasa Indonesia): see the docs/ folder of the repository.
| Product | Versions Compatible and additional computed target framework versions. |
|---|---|
| .NET | net10.0 is compatible. net10.0-android was computed. net10.0-browser was computed. net10.0-ios was computed. net10.0-maccatalyst was computed. net10.0-macos was computed. net10.0-tvos was computed. net10.0-windows was computed. |
-
net10.0
- Gravicode.MediaPipeNet.Tasks.Core (>= 1.0.0)
NuGet packages (4)
Showing the top 4 NuGet packages that depend on Gravicode.MediaPipeNet.Tasks.Audio:
| Package | Downloads |
|---|---|
|
Gravicode.MediaPipeNet
MediaPipe.NET — native .NET port of Google MediaPipe (face detection, face mesh, hand tracking, gestures, pose, holistic, segmentation, interactive segmentation, object detection, image classification and embedding, audio classification, voice activity detection, text classification and embedding, language detection) on ONNX Runtime. This package bundles the CPU runtime (plus CoreML on macOS) and works on Windows, Linux and macOS. Created by Gravicode Studios, led by Kang Fadhil. |
|
|
Gravicode.MediaPipeNet.DirectML
MediaPipe.NET with the DirectML (DirectX 12 GPU) ONNX Runtime for Windows — GPU acceleration on NVIDIA, AMD and Intel GPUs. Use instead of the MediaPipeNet package. Created by Gravicode Studios, led by Kang Fadhil. |
|
|
Gravicode.MediaPipeNet.Extensions.DI
Microsoft.Extensions.DependencyInjection integration for MediaPipe.NET: services.AddMediaPipeNet(...).AddFaceDetector().AddHandLandmarker()... registers thread-safe task singletons for ASP.NET Core and Worker Services, wired to ILogger. Created by Gravicode Studios, led by Kang Fadhil. |
|
|
Gravicode.MediaPipeNet.Cuda
MediaPipe.NET with the CUDA ONNX Runtime for NVIDIA GPUs on Windows and Linux (requires CUDA 12 and cuDNN 9). Use instead of the MediaPipeNet package. Created by Gravicode Studios, led by Kang Fadhil. |
GitHub repositories
This package is not used by any popular GitHub repositories.