feat: adauga --modules filter si la download.py

Parametrul din run.bat (ex: 4-5) era transmis doar la transcribe.py.
Acum download.py primeste acelasi filtru si descarca doar modulele
specificate. Sintaxa acceptata: '4-5', '1,3', '1-3,5'.

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

.gitattributes

@@ -0,0 +1,7 @@
+# Default: LF for all text files
+* text=auto eol=lf
+
+# Windows-only files must stay CRLF
+*.bat text eol=crlf
+*.cmd text eol=crlf
+*.ps1 text eol=crlf

download.py

@@ -49,6 +49,19 @@ def login(session: requests.Session, email: str, password: str) -> bool:
     return True
 
 
+def parse_module_filter(arg: str) -> set[int]:
+    """Parse module filter like '1-3' or '4,5' or '1-3,5' into a set of 1-based indices."""
+    result = set()
+    for part in arg.split(","):
+        part = part.strip()
+        if "-" in part:
+            a, b = part.split("-", 1)
+            result.update(range(int(a), int(b) + 1))
+        else:
+            result.add(int(part))
+    return result
+
+
 def discover_modules(session: requests.Session) -> list[dict]:
     """Fetch course page and return list of {name, url, module_id}."""
     resp = session.get(COURSE_URL)
@@ -157,6 +170,14 @@ def main():
         log.error("Set COURSE_USERNAME and COURSE_PASSWORD in .env")
         sys.exit(1)
 
+    # Parse --modules filter (e.g. "4-5" or "1,3,5")
+    module_filter = None
+    if "--modules" in sys.argv:
+        idx = sys.argv.index("--modules")
+        if idx + 1 < len(sys.argv):
+            module_filter = parse_module_filter(sys.argv[idx + 1])
+            log.info(f"Module filter: {sorted(module_filter)}")
+
     AUDIO_DIR.mkdir(exist_ok=True)
 
     session = requests.Session()
@@ -185,7 +206,10 @@ def main():
     skipped = 0
     failed = 0
 
-    for mod in modules:
+    for mod_idx, mod in enumerate(modules, 1):
+        if module_filter and mod_idx not in module_filter:
+            log.info(f"  Skipping module {mod_idx}: {mod['name']}")
+            continue
         lectures = discover_lectures(session, mod)
         module_entry = {
             "name": mod["name"],

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
@@ -20,17 +18,31 @@ set "NEED_WHISPER="
 set "NEED_MODEL="
 
 :: --- Python ---
-python --version >nul 2>&1
+:: Avoid executing python.exe directly — the Microsoft Store stub terminates cmd.exe.
-if errorlevel 1 (
+:: Use 'py' launcher first (safe), then find python.exe excluding WindowsApps stub.
+set "PYTHON_CMD="
+where py >nul 2>&1
+if not errorlevel 1 (
+    set "PYTHON_CMD=py"
+    for /f "tokens=2" %%v in ('py --version 2^>^&1') do echo [OK] Python         %%v (py launcher^)
+)
+if not defined PYTHON_CMD (
+    for /f "delims=" %%p in ('where python 2^>nul ^| findstr /v /i "WindowsApps"') do (
+        if not defined PYTHON_CMD (
+            set "PYTHON_CMD=%%p"
+            for /f "tokens=2" %%v in ('"%%p" --version 2^>^&1') do echo [OK] Python         %%v
+        )
+    )
+)
+if not defined PYTHON_CMD (
     echo [X] Python         NOT FOUND
+    echo     The Microsoft Store stub does not count as a real Python install.
     echo     Install from: https://www.python.org/downloads/
     echo     Make sure to check "Add Python to PATH" during install.
     echo.
     echo     Cannot continue without Python. Install it and re-run.
     pause
     exit /b 1
-) else (
-    for /f "tokens=2" %%v in ('python --version 2^>^&1') do echo [OK] Python         %%v
 )
 
 :: --- .env credentials ---
@@ -126,21 +138,6 @@ 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.
@@ -173,7 +170,7 @@ if defined NEED_FFMPEG (
     echo ============================================================
     echo  Auto-downloading ffmpeg...
     echo ============================================================
-    python setup_whisper.py ffmpeg
+    "!PYTHON_CMD!" setup_whisper.py ffmpeg
     if errorlevel 1 (
         echo.
         echo ERROR: Could not install ffmpeg.
@@ -193,9 +190,9 @@ 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
+    "!PYTHON_CMD!" setup_whisper.py whisper
     if errorlevel 1 (
         echo.
         echo ERROR: Failed to auto-download whisper.cpp.
@@ -217,7 +214,7 @@ if defined NEED_MODEL (
     echo  Auto-downloading Whisper model (ggml-medium-q5_0, ~500 MB^)...
     echo  This will take a few minutes depending on your connection.
     echo ============================================================
-    python setup_whisper.py model
+    "!PYTHON_CMD!" setup_whisper.py model
     if errorlevel 1 (
         echo.
         echo ERROR: Failed to download model.
@@ -242,7 +239,7 @@ echo.
 :: ============================================================
 if not exist ".venv\Scripts\python.exe" (
     echo [1/4] Creating Python virtual environment...
-    python -m venv .venv
+    "!PYTHON_CMD!" -m venv .venv
     if errorlevel 1 (
         echo ERROR: Failed to create venv.
         pause
@@ -268,7 +265,12 @@ echo      Done.
 echo.
 echo [3/4] Downloading audio files...
 echo ============================================================
-.venv\Scripts\python download.py
+if "%~1"=="" (
+    .venv\Scripts\python download.py
+) else (
+    echo Modules filter: %~1
+    .venv\Scripts\python download.py --modules %~1
+)
 if errorlevel 1 (
     echo.
     echo WARNING: Some downloads failed. Check download_errors.log

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
+    # Priority: CPU build (no GPU deps needed)
-    vulkan_asset = None
     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
+        # Skip GPU builds entirely
-        if "cuda" in name:
+        if "cuda" in name or "vulkan" in name or "openblas" in name:
             continue
-        if "vulkan" in name:
+        if "noavx" not in name:
-            vulkan_asset = asset
-            break
-        if "noavx" not in name and "openblas" not in name:
             cpu_asset = asset
+            break
 
-    chosen = vulkan_asset or cpu_asset
+    if not cpu_asset:
-    if not chosen:
+        print("  No CPU build found in official releases")
-        print("  No Vulkan or CPU-only 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 CPU build: {cpu_asset['name']}")
-        print(f"  Found official Vulkan build: {chosen['name']}")
+    chosen = cpu_asset
-    else:
-        print(f"  No Vulkan build in official release, using CPU build: {chosen['name']}")
-        print(f"  (Will work but without GPU acceleration)")
 
     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)
+        print(f"  whisper-cli.exe already exists at {whisper_exe}")
-        has_cuda = (WHISPER_DIR / "ggml-cuda.dll").exists()
+        return str(whisper_exe)
-        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)
 
-    # 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