https://github.com/jerryshell/whisper.cpp-windows-vulkan-bin
whisper.cpp Windows binary w/ Vulkan GPU support
https://github.com/jerryshell/whisper.cpp-windows-vulkan-bin
ai amd amd-gpu inference openai speech-recognition speech-to-text srt subtitles transformer vulkan whisper whisper-cpp
Last synced: 17 days ago
JSON representation
whisper.cpp Windows binary w/ Vulkan GPU support
- Host: GitHub
- URL: https://github.com/jerryshell/whisper.cpp-windows-vulkan-bin
- Owner: jerryshell
- Created: 2025-08-21T06:59:29.000Z (9 months ago)
- Default Branch: master
- Last Pushed: 2025-08-23T19:00:53.000Z (9 months ago)
- Last Synced: 2025-09-02T13:05:22.232Z (9 months ago)
- Topics: ai, amd, amd-gpu, inference, openai, speech-recognition, speech-to-text, srt, subtitles, transformer, vulkan, whisper, whisper-cpp
- Homepage:
- Size: 1.95 KB
- Stars: 1
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# whisper.cpp Windows binary w/ Vulkan GPU support
Get `whisper.cpp-windows-vulkan.zip` from the [Releases page](https://github.com/jerryshell/whisper.cpp-windows-vulkan-bin/releases)
## Example: Integration to Subtitle Edit
Copy file to `%appdata%\Subtitle Edit\Whisper\Cpp`
You may need to create the directory manually
## Example: Download and Transcribe YouTube video
Bash command
### Download video
```shell
yt-dlp \
-f "bestvideo[ext=mp4]+bestaudio[ext=m4a]/best[ext=mp4]/best" \
-o "video/1.mp4" \
--no-simulate \
--no-write-auto-subs \
--restrict-filenames \
--embed-thumbnail \
--embed-chapters \
--xattrs \
"https://www.youtube.com/watch?v=UF8uR6Z6KLc";
```
### Extract audio and Resample
```shell
ffmpeg \
-i "video/1.mp4" \
-hide_banner \
-vn \
-loglevel error \
-ar 16000 \
-ac 1 \
-c:a pcm_s16le \
-y \
"video/1.wav";
```
### Transcribe
https://huggingface.co/ggerganov/whisper.cpp
```shell
./whisper-cli \
-m "model/ggml-large-v2-q5_0.bin" \
-f "video/1.wav" \
-sns \
-osrt;
```
### Transcribe w/ VAD
https://huggingface.co/ggml-org/whisper-vad
```shell
./whisper-cli \
-m "model/ggml-large-v2-q5_0.bin" \
--vad \
-vm "model/ggml-silero-v5.1.2.bin" \
-f "video/1.wav" \
-sns \
-osrt;
```
## More usage
See [ggml-org/whisper.cpp](https://github.com/ggml-org/whisper.cpp)