Release v1.0.4: The Compatibility Update

- Added robust CPU Fallback for AMD/Non-CUDA GPUs.
- Implemented Lazy Load for AI Engine to prevent startup crashes.
- Added explicit DLL injection for Cublas/Cudnn on Windows.
- Added Corrupt Model Auto-Repair logic.
- Includes pre-compiled v1.0.4 executable.

RELEASE_NOTES.md

@@ -1,28 +1,28 @@
-# Release v1.0.2
+# Release v1.0.4
 
-**"The Lightweight Release"**
+**"The Compatibility Update"**
 
-This release focuses on removing bloat and switching to a native approach for punctuation, resulting in a significantly faster and smaller application.
+This release focuses on maximum stability across different hardware configurations (AMD, Intel, Nvidia) and fixing startup crashes related to corrupted models or missing drivers.
 
-## 🚀 Key Changes
+## 🛠️ Critical Fixes
 
-### 1. Style Prompting (Replaces Grammar Model)
-We have removed the heavy "Grammar Correction" model (M2M100) and replaced it with **Style Prompting**.
-*   **How it works**: Uses Whisper's internal context awareness to force proper punctuation.
-*   **New Settings**: Go to `Settings -> AI Engine` to choose a style:
-    *   **Standard**: (Default) Forces full sentences and proper punctuation.
-    *   **Casual**: Relaxed, lowercase style.
-    *   **Custom**: Enter your own prompt context.
+### 1. Robust CPU Fallback (AMD / Intel Support)
+*   **Problem**: Previously, if an AMD user tried to run the app, it would crash instantly because it tried to load Nvidia CUDA libraries by default.
+*   **Fix**: The app now **silently detects** if CUDA initialization fails (due to missing DLLs or incompatible hardware) and **automatically falls back to CPU mode**.
+*   **Result**: The app "just works" on any Windows machine, regardless of GPU.
 
-### 2. Bloat Removal
-*   **Removed**: `transformers`, `sentencepiece`, `accelerate` libraries.
-*   **Removed**: `grammar-m2m100` model downloader and logic.
-*   **Impact**: The application is lighter, installs faster, and uses less RAM.
+### 2. Startup Crash Protection
+*   **Problem**: If `faster_whisper` was imported before checking for valid drivers, the app would crash on launch for some users.
+*   **Fix**: Implemented **Lazy Loading** for the AI engine. The app now starts the UI first, and only loads the heavy AI libraries inside a safety block that catches errors.
 
-### 3. Stability Fixes
-*   **Fixed**: `NameError: 'torch' is not defined` when using Low VRAM Mode.
-*   **Fixed**: Bootstrapper now self-repairs missing dependencies if the environment gets corrupted.
+### 3. Corrupt Model Auto-Repair
+*   **Problem**: Interrupted downloads could leave a corrupted model folder, preventing the app from ever starting again.
+*   **Fix**: If the app detects a "vocabulary missing" or invalid config error, it will now **automatically delete the corrupt folder** and allow you to re-download it cleanly.
+
+### 4. Windows DLL Injection
+*   **Fix**: Added explicit DLL path injection for `nvidia-cublas` and `nvidia-cudnn` to ensure Python 3.8+ can find the required CUDA libraries on Windows systems that don't have them in PATH.
 
 ## 📦 Installation
-1.  Download `WhisperVoice.exe` (attached below or in `dist/`).
-2.  Run it. It will automatically update your environment if needed.
+1.  Download `WhisperVoice.exe` below.
+2.  Replace your existing `.exe`.
+3.  Run it.