This feature and documentation were contributed by GitHub phoenixlyq.

Pre-installation:
Download .NET Runtime (choose latest .NET 8 or .NET 9)
VC++ Redistributable (Microsoft official)
After installing both, restart your computer before running the software.

Note: The Windows pre-packaged version does NOT include the dependencies for this service. To use it, deploy from source and follow the instructions below.Complex environment issues may arise. If errors persist after following the instructions, consider switching to faster-whisper.

What is This?

Whisper.NET is a speech recognition engine that enables AMD GPU acceleration via Vulkan (no NVIDIA CUDA required).

Use Case

Designed for Windows + AMD GPU users.

Background: The latest version of Whisper.cpp no longer provides AMD GPU support on Windows, meaning Windows + AMD GPU users can only use CPU for speech recognition — very slow. After consulting with AI, we chose the Whisper.NET approach.

Tested Environment: Currently tested on Windows 11 23H2 + RX 6650 XT. Other environments may require testing. Feedback is welcome.

Step 1: Download DLL Files

Required Files

Managed DLLs (place in deps/ folder):

Open the download page, click "Download package" in the right sidebar to download a .nupkg file. Rename the extension to .zip and extract. Find the DLL files in the extracted folder or lib/ subfolder (netstandard2.0 / netstandard8.0 / netstandard462). Copy them to deps/ in the sp.exe/sp.py folder (create deps if needed).

File	Version	Download Link
Whisper.net.dll	1.9.0	Download
Microsoft.Extensions.AI.Abstractions.dll	10.0.0	Download
Microsoft.Bcl.AsyncInterfaces.dll	10.0.0	Download
System.Memory.dll	4.6.3	Download
System.Buffers.dll	4.6.1	Download
System.Runtime.CompilerServices.Unsafe.dll	6.1.2	Download
System.Numerics.Vectors.dll	4.6.1	Download

Native DLLs (place in deps/native/ folder):

Open Whisper.net.Runtime.Vulkan 1.9.0, click "Download package", rename .nupkg to .zip, extract, and copy all DLL files from build/win-x64/ to deps/native/.

The NuGet package contains these files (all required, rename aliases after copying):

File	Size	Purpose
whisper.dll	473KB	Speech recognition core
libwhisper.dll	473KB	Copy and rename whisper.dll → libwhisper.dll (alias, required)
ggml-whisper.dll	66KB	Compute library
libggml-whisper.dll	66KB	Rename ggml-whisper.dll → libggml-whisper.dll (alias)
ggml-base-whisper.dll	528KB	Base library (required dependency)
libggml-base-whisper.dll	528KB	Rename ggml-base-whisper.dll → libggml-base-whisper.dll (alias)
ggml-cpu-whisper.dll	590KB	CPU backend
libggml-cpu-whisper.dll	590KB	Rename ggml-cpu-whisper.dll → libggml-cpu-whisper.dll (alias)
ggml-vulkan-whisper.dll	45MB	GPU acceleration (Vulkan)
libggml-vulkan-whisper.dll	45MB	Rename ggml-vulkan-whisper.dll → libggml-vulkan-whisper.dll (alias)

Step 2: Download Speech Model

Download .bin format model files from ggerganov/whisper.cpp models and place them in the models/ folder.

Recommended: ggml-large-v3-turbo.bin (good quality, fast)

Step 3: Verify File Structure

Ensure your directory structure looks like this:

pyvideotrans/
├─ models/
│  └─ ggml-large-v3-turbo.bin    ← Speech model
└─ deps/
   ├─ Whisper.net.dll            ← Managed DLLs (7 files)
   ├─ Microsoft.Extensions.AI.Abstractions.dll
   ├─ Microsoft.Bcl.AsyncInterfaces.dll
   ├─ System.Memory.dll
   ├─ System.Buffers.dll
   ├─ System.Runtime.CompilerServices.Unsafe.dll
   ├─ System.Numerics.Vectors.dll
   └─ native/                     ← All DLLs from build/win-x64/
      ├─ whisper.dll
      ├─ libwhisper.dll
      ├─ ggml-whisper.dll
      ├─ libggml-whisper.dll
      ├─ ggml-base-whisper.dll
      ├─ libggml-base-whisper.dll
      ├─ ggml-cpu-whisper.dll
      ├─ libggml-cpu-whisper.dll
      ├─ ggml-vulkan-whisper.dll
      └─ libggml-vulkan-whisper.dll

Step 4: Start Using

Deploy from source, run uv sync --all-extras. If already installed, run uv sync --extra dotnet to install the pythonnet module.
Run uv run sp.py to open the software.
Select "Whisper.NET" from the speech recognition dropdown.
Choose your downloaded model file.
Click Start.

Troubleshooting

"Native Library not found" or error code `0x8007007E`

Check that deps/native/ folder contains all 10 DLL files.
Verify file names are correct.

GPU acceleration not working

Update your graphics driver.
AMD GPUs require Vulkan support (RX 400 series or newer).
NVIDIA GPUs require GTX 600 series or newer.

pythonnet initialization failed

Install .NET Runtime (choose the latest .NET 8 or .NET 9).

Check if your GPU supports Vulkan

Open command line and run:

vulkaninfo

If it displays your GPU information, Vulkan is supported.

Whisper.NET Setup Guide

What is this?

Whisper.NET is a speech recognition engine that uses Vulkan acceleration for AMD GPUs (no NVIDIA CUDA required).

Use Case

Designed for Windows + AMD GPU users.

Background: The latest Whisper.cpp version no longer provides AMD GPU support on Windows, so Windows + AMD GPU users can only use CPU for speech recognition, which is very slow. After consulting and discussing with AI, I chose the Whisper.NET approach and implemented it with AI assistance.

Tested Environment: Currently only tested on Windows 11 23H2 + RX 6650 XT. Other environments may need further testing. Feedback is welcome.

Step 1: Download DLL Files

Required Files

Managed DLLs (place in deps/ folder):

File	Version	Download Link
Whisper.net.dll	1.9.0	Download
Microsoft.Extensions.AI.Abstractions.dll	10.0.0	Download
Microsoft.Bcl.AsyncInterfaces.dll	10.0.0	Download
System.Memory.dll	4.6.3	Download
System.Buffers.dll	4.6.1	Download
System.Runtime.CompilerServices.Unsafe.dll	6.1.2	Download
System.Numerics.Vectors.dll	4.6.1	Download

Native DLLs (place in deps/native/ folder):

Download from Whisper.net.Runtime.Vulkan 1.9.0, extract and copy all DLL files from build/win-x64/ to deps/native/.

The NuGet package contains these files (all required):

File	Size	Purpose
whisper.dll	473KB	Speech recognition core
libwhisper.dll	473KB	Alias for whisper.dll (required)
ggml-whisper.dll	66KB	Compute library
libggml-whisper.dll	66KB	Alias for ggml-whisper.dll
ggml-base-whisper.dll	528KB	Base library (required dependency)
libggml-base-whisper.dll	528KB	Alias for ggml-base-whisper.dll
ggml-cpu-whisper.dll	590KB	CPU backend
libggml-cpu-whisper.dll	590KB	Alias for ggml-cpu-whisper.dll
ggml-vulkan-whisper.dll	45MB	GPU acceleration (Vulkan)
libggml-vulkan-whisper.dll	45MB	Alias for ggml-vulkan-whisper.dll

How to download from NuGet?

Click the download link above to open the NuGet page.
Click "Download package" to download the .nupkg file.
Rename the .nupkg extension to .zip and open with any archive tool.
Find the DLL files inside:
- Managed DLLs are in lib/netstandard2.0/ folder.
- Native DLLs are in build/win-x64/ folder.

Step 2: Download Speech Model

Download .bin format model files from ggerganov/whisper.cpp models and place them in the models/ folder.

Recommended: ggml-large-v3-turbo.bin (good quality, fast)

Step 3: Verify File Structure

Make sure your directory structure looks like this:

pyvideotrans/
├─ models/
│  └─ ggml-large-v3-turbo.bin    ← Speech model
└─ deps/
   ├─ Whisper.net.dll            ← Managed DLLs (7 files)
   ├─ Microsoft.Extensions.AI.Abstractions.dll
   ├─ Microsoft.Bcl.AsyncInterfaces.dll
   ├─ System.Memory.dll
   ├─ System.Buffers.dll
   ├─ System.Runtime.CompilerServices.Unsafe.dll
   ├─ System.Numerics.Vectors.dll
   └─ native/                     ← Copy all DLLs from build/win-x64/ here
      ├─ whisper.dll
      ├─ libwhisper.dll
      ├─ ggml-whisper.dll
      ├─ libggml-whisper.dll
      ├─ ggml-base-whisper.dll
      ├─ libggml-base-whisper.dll
      ├─ ggml-cpu-whisper.dll
      ├─ libggml-cpu-whisper.dll
      ├─ ggml-vulkan-whisper.dll
      └─ libggml-vulkan-whisper.dll

Step 4: Start Using

Open pyVideoTrans.
Select "Whisper.NET" from the speech recognition dropdown.
Choose your downloaded model file.
Click Start.

Troubleshooting

"Native Library not found" or error code `0x8007007E`

Check if deps/native/ folder contains all 10 DLL files.
Verify file names are correct.

GPU acceleration not working

Update your graphics driver.
AMD GPUs require Vulkan support (RX 400 series or newer).
NVIDIA GPUs require GTX 600 series or newer.

pythonnet initialization failed

Install .NET Runtime (choose the latest .NET 8 or .NET 9).

Check if your GPU supports Vulkan

Open command line and run:

vulkaninfo

If it displays your GPU information, Vulkan is supported.

What is This? ​

Use Case ​

Step 1: Download DLL Files ​

Required Files ​

Step 2: Download Speech Model ​

Step 3: Verify File Structure ​

Step 4: Start Using ​

Troubleshooting ​

"Native Library not found" or error code 0x8007007E ​

GPU acceleration not working ​

pythonnet initialization failed ​

Check if your GPU supports Vulkan ​

Whisper.NET Setup Guide ​

What is this? ​

Use Case ​

Step 1: Download DLL Files ​

Required Files ​

How to download from NuGet? ​

Step 2: Download Speech Model ​

Step 3: Verify File Structure ​

Step 4: Start Using ​

Troubleshooting ​

"Native Library not found" or error code 0x8007007E ​

GPU acceleration not working ​

pythonnet initialization failed ​

Check if your GPU supports Vulkan ​

What is This?

Use Case

Step 1: Download DLL Files

Required Files

Step 2: Download Speech Model

Step 3: Verify File Structure

Step 4: Start Using

Troubleshooting

"Native Library not found" or error code `0x8007007E`

GPU acceleration not working

pythonnet initialization failed

Check if your GPU supports Vulkan

Whisper.NET Setup Guide

What is this?

Use Case

Step 1: Download DLL Files

Required Files

How to download from NuGet?

Step 2: Download Speech Model

Step 3: Verify File Structure

Step 4: Start Using

Troubleshooting

"Native Library not found" or error code `0x8007007E`

GPU acceleration not working

pythonnet initialization failed

Check if your GPU supports Vulkan