Skip to content

fix(linux): enable GPU acceleration for ONNX models #1298

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
aasmall wants to merge 1 commit into from
Closed

fix(linux): enable GPU acceleration for ONNX models #1298

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion src-tauri/Cargo.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -105,7 +105,7 @@ transcribe-rs = { version = "0.3.3", features = ["whisper-metal"] }
[target.'cfg(target_os = "linux")'.dependencies]
gtk-layer-shell = { version = "0.8", features = ["v0_6"] }
gtk = "0.18"
transcribe-rs = { version = "0.3.3", features = ["whisper-vulkan"] }
transcribe-rs = { version = "0.3.8", features = ["whisper-cpp", "onnx", "whisper-vulkan", "ort-rocm", "ort-cuda"] }

[patch.crates-io]
tauri-runtime = { git = "https://github.com/cjpais/tauri.git", branch = "handy-2.10.2" }
Expand Down
4 changes: 2 additions & 2 deletions src/i18n/locales/en/translation.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -258,11 +258,11 @@
"acceleration": {
"whisper": {
"title": "Whisper Acceleration",
"description": "Hardware acceleration for Whisper models. Auto uses GPU if available (Metal on macOS, Vulkan on Windows/Linux)."
"description": "GPU acceleration for Whisper models only. Does not affect Parakeet, Canary, or Moonshine — those use ONNX Acceleration below. Auto uses Metal on macOS, Vulkan on Windows/Linux."
},
"ort": {
"title": "ONNX Acceleration",
"description": "Hardware acceleration for ONNX models (Parakeet, Canary, Moonshine, etc.). DirectML on Windows is experimental. Models may fail to transcribe."
"description": "GPU acceleration for ONNX models: Parakeet, Canary, Moonshine, SenseVoice, etc. Does not affect Whisper models. Linux: ROCm (AMD) or CUDA (NVIDIA). Windows: DirectML. macOS: CPU only."
},
"gpuDevice": {
"title": "GPU Device",
Expand Down