Aura v1.0.8
·
118 commits
to 66f91686100896b3028324c5f2bc83258f120a18
since this release
What's Changed:
- Resident Whisper Server on CUDA: Introduced resident background server execution (
whisper-server.exe) insrc-tauri/src/whisper_runner.rsalongside Parakeet's resident server. When NVIDIA CUDA acceleration is active, the server keeps model weights (e.g.large-v3-turbo-q5_0) loaded directly in GPU VRAM (CUDA0), dropping transcription latency from ~15s cold starts down to ~250ms on discrete GPUs. - Unified On-Demand CUDA Package Downloader: Extended
download_gpu_binaries_innerinsrc-tauri/src/lib.rsto download, SHA-256 verify, and extract both the Sherpa-ONNX CUDA runtime (sherpa-onnx-v1.13.4-win-x64-cuda.tar.bz2) and Whisper cuBLAS runtime (whisper-cublas-11.8.0-bin-x64.zipcontainingggml-cuda.dll) into%LOCALAPPDATA%\com.aura.app\binaries\cuda\bin\. This enables one-click GPU acceleration for both engines while keeping the base installer compact (~20–25 MB). - Dynamic Working Directory DLL Routing: Configured
start_whisper_server_unlockedandrun_local_whisperinsrc-tauri/src/whisper_runner.rsto set their process working directory andPATHto%LOCALAPPDATA%\com.aura.app\binaries\cuda\bin\when CUDA is selected. This allowsggml.dll'sggml_backend_load_all()to dynamically detectggml-cuda.dlland initializeCUDA0without requiring DLL copies to system directories. - Model Verification Spinner & State Feedback: Added a dedicated
statusfield toDownloadProgressinsrc-tauri/src/whisper_runner.rsand updatedsrc/main.jsto transition download cards into an animatedinstallingstate with a circular spinner during post-download SHA-256 integrity verification, eliminating the static 5–10s freeze at 100% on large model files. - Native Neural Punctuation Transition: Removed legacy
CT-Transformerexternal dependency and heuristic string manipulation (apply_voice_punctuation) insrc-tauri/src/whisper_runner.rsin favor of native acoustic punctuation built into Whisper and Parakeet models, eliminating punctuation duplication and word trimming artifacts. - Overlay Timer & Status Customization: Added the
overlay_show_timertoggle insrc-tauri/src/settings.rsandsrc/main.js, allowing users to hide duration counters and status labels from the floating overlay capsule while keeping the audio visualizer and critical error alerts intact. - Full 9-Language Localization Parity: Synchronized and filled all translation keys across all 9 supported locales (
ru,en,de,es,fr,it,zh,pt,tr) insrc/main.js, strictly validated by automated tests intests/frontend-static.test.mjs. - Automated CI/CD Release Publishing: Updated
.github/workflows/release.yml(releaseDraft: false) and configuredosv-scanner.tomldependency filters to ensure production installer artifacts (.exe,.msi,.sig) build, sign, and publish automatically upon tag creation.