feat: switch to CPU-only whisper build (no GPU on this machine)

- setup_whisper.py: descarcă build CPU din release-urile oficiale,
  sare peste Vulkan/CUDA/OpenBLAS
- run.bat: elimină env var GGML_VK_PREFER_HOST_MEMORY și check-ul Vulkan SDK
- transcribe.py: --no-gpu era deja setat

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

run.bat

@@ -2,8 +2,6 @@
 setlocal enabledelayedexpansion
 cd /d "%~dp0"
 
-:: Prevent Vulkan from exhausting VRAM — overflow to system RAM instead of crashing
-set "GGML_VK_PREFER_HOST_MEMORY=ON"
 
 echo ============================================================
 echo  NLP Master - Download + Transcribe Pipeline
@@ -126,21 +124,6 @@ if exist "%WHISPER_MODEL%" (
     set "NEED_MODEL=1"
 )
 
-:: --- Vulkan GPU support ---
-set "VULKAN_FOUND="
-where vulkaninfo >nul 2>&1
-if not errorlevel 1 (
-    set "VULKAN_FOUND=1"
-    echo [OK] Vulkan SDK      Installed
-) else (
-    if exist "%VULKAN_SDK%\Bin\vulkaninfo.exe" (
-        set "VULKAN_FOUND=1"
-        echo [OK] Vulkan SDK      %VULKAN_SDK%
-    ) else (
-        echo [!!] Vulkan SDK      Not detected (whisper.cpp may use CPU fallback^)
-        echo      Install from: https://vulkan.lunarg.com/sdk/home
-    )
-)
 
 :: --- Disk space ---
 echo.
@@ -193,7 +176,7 @@ if exist "ffmpeg-bin\ffmpeg.exe" (
 
 if defined NEED_WHISPER (
     echo ============================================================
-    echo  Auto-downloading whisper.cpp (Vulkan build^)...
+    echo  Auto-downloading whisper.cpp (CPU build^)...
     echo ============================================================
     python setup_whisper.py whisper
     if errorlevel 1 (

setup_whisper.py

@@ -1,5 +1,5 @@
 """
-Auto-download and setup whisper.cpp (Vulkan) + model for Windows.
+Auto-download and setup whisper.cpp (CPU build) + model for Windows.
 Called by run.bat when prerequisites are missing.
 """
 
@@ -142,8 +142,7 @@ def try_official_vulkan_build() -> str | None:
     tag = release.get("tag_name", "unknown")
     print(f"  Official release: {tag}")
 
-    # Priority: vulkan > noavx (cpu-only, no CUDA deps) > skip CUDA entirely
-    vulkan_asset = None
+    # Priority: CPU build (no GPU deps needed)
     cpu_asset = None
     for asset in release.get("assets", []):
         name = asset["name"].lower()
@@ -152,28 +151,22 @@ def try_official_vulkan_build() -> str | None:
         # Must be Windows
         if "win" not in name and "x64" not in name:
             continue
-        # Absolutely skip CUDA builds - they won't work on AMD
-        if "cuda" in name:
+        # Skip GPU builds entirely
+        if "cuda" in name or "vulkan" in name or "openblas" in name:
             continue
-        if "vulkan" in name:
-            vulkan_asset = asset
-            break
-        if "noavx" not in name and "openblas" not in name:
+        if "noavx" not in name:
             cpu_asset = asset
+            break
 
-    chosen = vulkan_asset or cpu_asset
-    if not chosen:
-        print("  No Vulkan or CPU-only build found in official releases")
+    if not cpu_asset:
+        print("  No CPU build found in official releases")
         print("  Available assets:")
         for asset in release.get("assets", []):
             print(f"    - {asset['name']}")
         return None
 
-    if vulkan_asset:
-        print(f"  Found official Vulkan build: {chosen['name']}")
-    else:
-        print(f"  No Vulkan build in official release, using CPU build: {chosen['name']}")
-        print(f"  (Will work but without GPU acceleration)")
+    print(f"  Found CPU build: {cpu_asset['name']}")
+    chosen = cpu_asset
 
     zip_path = Path(chosen["name"])
     download_file(chosen["browser_download_url"], zip_path, chosen["name"])
@@ -182,29 +175,12 @@ def try_official_vulkan_build() -> str | None:
 
 
 def setup_whisper_bin() -> str | None:
-    """Download whisper.cpp Vulkan release. Returns path to whisper-cli.exe."""
+    """Download whisper.cpp CPU release. Returns path to whisper-cli.exe."""
     whisper_exe = WHISPER_DIR / "whisper-cli.exe"
     if whisper_exe.exists():
-        # Check if it's a CUDA build (has CUDA DLLs but no Vulkan DLL)
-        has_cuda = (WHISPER_DIR / "ggml-cuda.dll").exists()
-        has_vulkan = (WHISPER_DIR / "ggml-vulkan.dll").exists()
-        if has_cuda and not has_vulkan:
-            print(f"  WARNING: Existing install is a CUDA build (won't work on AMD GPU)")
-            print(f"  Removing and re-downloading Vulkan build...")
-            import shutil
-            shutil.rmtree(WHISPER_DIR)
-        else:
-            print(f"  whisper-cli.exe already exists at {whisper_exe}")
-            return str(whisper_exe)
+        print(f"  whisper-cli.exe already exists at {whisper_exe}")
+        return str(whisper_exe)
 
-    # Strategy: try community Vulkan build first (reliable for AMD),
-    # then fall back to official release
-    exe_path = try_community_vulkan_build()
-    if exe_path:
-        print(f"\n  whisper-cli.exe ready at: {exe_path} (Vulkan)")
-        return exe_path
-
-    print("\n  Community build failed, trying official release...")
     exe_path = try_official_vulkan_build()
     if exe_path:
         print(f"\n  whisper-cli.exe ready at: {exe_path}")
@@ -212,7 +188,6 @@ def setup_whisper_bin() -> str | None:
 
     print("\n  ERROR: Could not download whisper.cpp")
     print("  Manual install: https://github.com/ggml-org/whisper.cpp/releases")
-    print("  Build from source with: cmake -DGGML_VULKAN=1")
     return None