romfast/nlp-master
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

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

Browse Source 
- 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>
This commit is contained in:
Marius Mutu
2026-03-24 02:01:39 +02:00
parent 60f564c107
commit e83bd74813
2 changed files with 309 additions and 351 deletions
Download Patch File Download Diff File Expand all files Collapse all files

609
run.bat
View File

@@ -1,313 +1,296 @@
@echo off
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
echo ============================================================
echo.
:: ============================================================
:: PREREQUISITES CHECK
:: ============================================================
echo Checking prerequisites...
echo.
set "PREREQ_OK=1"
set "NEED_WHISPER="
set "NEED_MODEL="
:: --- Python ---
python --version >nul 2>&1
if errorlevel 1 (
echo [X] Python NOT FOUND
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 ---
if exist ".env" (
findstr /m "COURSE_USERNAME=." ".env" >nul 2>&1
if errorlevel 1 (
echo [X] .env File exists but COURSE_USERNAME is empty
echo Edit .env and fill in your credentials.
set "PREREQ_OK="
) else (
echo [OK] .env Credentials configured
)
) else (
echo [X] .env NOT FOUND
echo Create .env with:
echo COURSE_USERNAME=your_email
echo COURSE_PASSWORD=your_password
set "PREREQ_OK="
)
:: --- ffmpeg ---
set "FFMPEG_FOUND="
set "NEED_FFMPEG="
where ffmpeg >nul 2>&1
if not errorlevel 1 (
set "FFMPEG_FOUND=1"
for /f "delims=" %%p in ('where ffmpeg 2^>nul') do set "FFMPEG_LOCATION=%%p"
echo [OK] ffmpeg !FFMPEG_LOCATION!
) else (
if exist "ffmpeg.exe" (
set "FFMPEG_FOUND=1"
echo [OK] ffmpeg .\ffmpeg.exe (local^)
) else (
echo [--] ffmpeg Not found - will auto-install
set "NEED_FFMPEG=1"
)
)
:: --- whisper-cli.exe ---
set "WHISPER_FOUND="
set "WHISPER_LOCATION="
if defined WHISPER_BIN (
if exist "%WHISPER_BIN%" (
set "WHISPER_FOUND=1"
set "WHISPER_LOCATION=%WHISPER_BIN% (env var)"
)
)
if not defined WHISPER_FOUND (
where whisper-cli.exe >nul 2>&1
if not errorlevel 1 (
set "WHISPER_FOUND=1"
for /f "delims=" %%p in ('where whisper-cli.exe 2^>nul') do set "WHISPER_LOCATION=%%p (PATH)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper-cli.exe"
set "WHISPER_LOCATION=.\whisper-cli.exe (local)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper-bin\whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper-bin\whisper-cli.exe"
set "WHISPER_LOCATION=whisper-bin\whisper-cli.exe (auto-installed)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper.cpp\build\bin\Release\whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper.cpp\build\bin\Release\whisper-cli.exe"
set "WHISPER_LOCATION=whisper.cpp\build\... (local build)"
)
)
if defined WHISPER_FOUND (
echo [OK] whisper-cli !WHISPER_LOCATION!
) else (
echo [--] whisper-cli Not found - will auto-download
set "NEED_WHISPER=1"
)
:: --- Whisper model ---
if not defined WHISPER_MODEL set "WHISPER_MODEL=models\ggml-medium-q5_0.bin"
if exist "%WHISPER_MODEL%" (
for %%F in ("%WHISPER_MODEL%") do (
set /a "MODEL_MB=%%~zF / 1048576"
)
echo [OK] Whisper model %WHISPER_MODEL% (!MODEL_MB! MB^)
) else (
echo [--] Whisper model Not found - will auto-download (~500 MB^)
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.
for /f "tokens=3" %%a in ('dir /-c "%~dp0." 2^>nul ^| findstr /c:"bytes free"') do (
set /a "FREE_GB=%%a / 1073741824" 2>nul
)
if defined FREE_GB (
if !FREE_GB! LSS 50 (
echo [!!] Disk space ~!FREE_GB! GB free (need ~50 GB for all audio + transcripts^)
) else (
echo [OK] Disk space ~!FREE_GB! GB free
)
)
echo.
:: --- Stop if .env is broken (can't auto-fix that) ---
if not defined PREREQ_OK (
echo ============================================================
echo MISSING PREREQUISITES - fix the [X] items above and re-run.
echo ============================================================
pause
exit /b 1
)
:: ============================================================
:: AUTO-INSTALL MISSING COMPONENTS
:: ============================================================
if defined NEED_FFMPEG (
echo ============================================================
echo Auto-downloading ffmpeg...
echo ============================================================
python setup_whisper.py ffmpeg
if errorlevel 1 (
echo.
echo ERROR: Could not install ffmpeg.
echo Download manually from: https://www.gyan.dev/ffmpeg/builds/
echo Extract ffmpeg.exe to ffmpeg-bin\ and re-run.
pause
exit /b 1
)
if exist ".ffmpeg_bin_path" del .ffmpeg_bin_path
echo.
)
:: Add ffmpeg-bin to PATH if it exists
if exist "ffmpeg-bin\ffmpeg.exe" (
set "PATH=%~dp0ffmpeg-bin;%PATH%"
)
if defined NEED_WHISPER (
echo ============================================================
echo Auto-downloading whisper.cpp (Vulkan build^)...
echo ============================================================
python setup_whisper.py whisper
if errorlevel 1 (
echo.
echo ERROR: Failed to auto-download whisper.cpp.
echo Download manually from: https://github.com/ggml-org/whisper.cpp/releases
pause
exit /b 1
)
:: Read the path that setup_whisper.py wrote
if exist ".whisper_bin_path" (
set /p WHISPER_BIN=<.whisper_bin_path
del .whisper_bin_path
echo Using: !WHISPER_BIN!
)
echo.
)
if defined NEED_MODEL (
echo ============================================================
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
if errorlevel 1 (
echo.
echo ERROR: Failed to download model.
echo Download manually from:
echo https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium-q5_0.bin
echo Save to: models\ggml-medium-q5_0.bin
pause
exit /b 1
)
echo.
)
echo All prerequisites OK!
echo.
echo ============================================================
echo Starting pipeline...
echo ============================================================
echo.
:: ============================================================
:: STEP 1: VENV + DEPENDENCIES
:: ============================================================
if not exist ".venv\Scripts\python.exe" (
echo [1/4] Creating Python virtual environment...
python -m venv .venv
if errorlevel 1 (
echo ERROR: Failed to create venv.
pause
exit /b 1
)
echo Done.
) else (
echo [1/4] Virtual environment already exists.
)
echo [2/4] Installing Python dependencies...
.venv\Scripts\pip install -q -r requirements.txt
if errorlevel 1 (
echo ERROR: Failed to install dependencies.
pause
exit /b 1
)
echo Done.
:: ============================================================
:: STEP 2: DOWNLOAD
:: ============================================================
echo.
echo [3/4] Downloading audio files...
echo ============================================================
.venv\Scripts\python download.py
if errorlevel 1 (
echo.
echo WARNING: Some downloads failed. Check download_errors.log
echo Press any key to continue to transcription anyway, or Ctrl+C to abort.
pause >nul
)
:: ============================================================
:: STEP 3: TRANSCRIBE
:: ============================================================
echo.
echo [4/4] Transcribing with whisper.cpp...
echo ============================================================
echo Using: %WHISPER_BIN%
echo Model: %WHISPER_MODEL%
echo.
if "%~1"=="" (
.venv\Scripts\python transcribe.py
) else (
echo Modules filter: %~1
.venv\Scripts\python transcribe.py --modules %~1
)
if errorlevel 1 (
echo.
echo WARNING: Some transcriptions failed. Check transcribe_errors.log
)
:: ============================================================
:: DONE
:: ============================================================
echo.
echo ============================================================
echo Pipeline complete!
echo - Audio files: audio\
echo - Transcripts: transcripts\
echo - Manifest: manifest.json
echo.
echo Next step: generate summaries from WSL2 with Claude Code
echo python summarize.py
echo ============================================================
pause
@echo off
setlocal enabledelayedexpansion
cd /d "%~dp0"
echo ============================================================
echo NLP Master - Download + Transcribe Pipeline
echo ============================================================
echo.
:: ============================================================
:: PREREQUISITES CHECK
:: ============================================================
echo Checking prerequisites...
echo.
set "PREREQ_OK=1"
set "NEED_WHISPER="
set "NEED_MODEL="
:: --- Python ---
python --version >nul 2>&1
if errorlevel 1 (
echo [X] Python NOT FOUND
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 ---
if exist ".env" (
findstr /m "COURSE_USERNAME=." ".env" >nul 2>&1
if errorlevel 1 (
echo [X] .env File exists but COURSE_USERNAME is empty
echo Edit .env and fill in your credentials.
set "PREREQ_OK="
) else (
echo [OK] .env Credentials configured
)
) else (
echo [X] .env NOT FOUND
echo Create .env with:
echo COURSE_USERNAME=your_email
echo COURSE_PASSWORD=your_password
set "PREREQ_OK="
)
:: --- ffmpeg ---
set "FFMPEG_FOUND="
set "NEED_FFMPEG="
where ffmpeg >nul 2>&1
if not errorlevel 1 (
set "FFMPEG_FOUND=1"
for /f "delims=" %%p in ('where ffmpeg 2^>nul') do set "FFMPEG_LOCATION=%%p"
echo [OK] ffmpeg !FFMPEG_LOCATION!
) else (
if exist "ffmpeg.exe" (
set "FFMPEG_FOUND=1"
echo [OK] ffmpeg .\ffmpeg.exe (local^)
) else (
echo [--] ffmpeg Not found - will auto-install
set "NEED_FFMPEG=1"
)
)
:: --- whisper-cli.exe ---
set "WHISPER_FOUND="
set "WHISPER_LOCATION="
if defined WHISPER_BIN (
if exist "%WHISPER_BIN%" (
set "WHISPER_FOUND=1"
set "WHISPER_LOCATION=%WHISPER_BIN% (env var)"
)
)
if not defined WHISPER_FOUND (
where whisper-cli.exe >nul 2>&1
if not errorlevel 1 (
set "WHISPER_FOUND=1"
for /f "delims=" %%p in ('where whisper-cli.exe 2^>nul') do set "WHISPER_LOCATION=%%p (PATH)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper-cli.exe"
set "WHISPER_LOCATION=.\whisper-cli.exe (local)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper-bin\whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper-bin\whisper-cli.exe"
set "WHISPER_LOCATION=whisper-bin\whisper-cli.exe (auto-installed)"
)
)
if not defined WHISPER_FOUND (
if exist "whisper.cpp\build\bin\Release\whisper-cli.exe" (
set "WHISPER_FOUND=1"
set "WHISPER_BIN=whisper.cpp\build\bin\Release\whisper-cli.exe"
set "WHISPER_LOCATION=whisper.cpp\build\... (local build)"
)
)
if defined WHISPER_FOUND (
echo [OK] whisper-cli !WHISPER_LOCATION!
) else (
echo [--] whisper-cli Not found - will auto-download
set "NEED_WHISPER=1"
)
:: --- Whisper model ---
if not defined WHISPER_MODEL set "WHISPER_MODEL=models\ggml-medium-q5_0.bin"
if exist "%WHISPER_MODEL%" (
for %%F in ("%WHISPER_MODEL%") do (
set /a "MODEL_MB=%%~zF / 1048576"
)
echo [OK] Whisper model %WHISPER_MODEL% (!MODEL_MB! MB^)
) else (
echo [--] Whisper model Not found - will auto-download (~500 MB^)
set "NEED_MODEL=1"
)
:: --- Disk space ---
echo.
for /f "tokens=3" %%a in ('dir /-c "%~dp0." 2^>nul ^| findstr /c:"bytes free"') do (
set /a "FREE_GB=%%a / 1073741824" 2>nul
)
if defined FREE_GB (
if !FREE_GB! LSS 50 (
echo [!!] Disk space ~!FREE_GB! GB free (need ~50 GB for all audio + transcripts^)
) else (
echo [OK] Disk space ~!FREE_GB! GB free
)
)
echo.
:: --- Stop if .env is broken (can't auto-fix that) ---
if not defined PREREQ_OK (
echo ============================================================
echo MISSING PREREQUISITES - fix the [X] items above and re-run.
echo ============================================================
pause
exit /b 1
)
:: ============================================================
:: AUTO-INSTALL MISSING COMPONENTS
:: ============================================================
if defined NEED_FFMPEG (
echo ============================================================
echo Auto-downloading ffmpeg...
echo ============================================================
python setup_whisper.py ffmpeg
if errorlevel 1 (
echo.
echo ERROR: Could not install ffmpeg.
echo Download manually from: https://www.gyan.dev/ffmpeg/builds/
echo Extract ffmpeg.exe to ffmpeg-bin\ and re-run.
pause
exit /b 1
)
if exist ".ffmpeg_bin_path" del .ffmpeg_bin_path
echo.
)
:: Add ffmpeg-bin to PATH if it exists
if exist "ffmpeg-bin\ffmpeg.exe" (
set "PATH=%~dp0ffmpeg-bin;%PATH%"
)
if defined NEED_WHISPER (
echo ============================================================
echo Auto-downloading whisper.cpp (CPU build^)...
echo ============================================================
python setup_whisper.py whisper
if errorlevel 1 (
echo.
echo ERROR: Failed to auto-download whisper.cpp.
echo Download manually from: https://github.com/ggml-org/whisper.cpp/releases
pause
exit /b 1
)
:: Read the path that setup_whisper.py wrote
if exist ".whisper_bin_path" (
set /p WHISPER_BIN=<.whisper_bin_path
del .whisper_bin_path
echo Using: !WHISPER_BIN!
)
echo.
)
if defined NEED_MODEL (
echo ============================================================
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
if errorlevel 1 (
echo.
echo ERROR: Failed to download model.
echo Download manually from:
echo https://huggingface.co/ggerganov/whisper.cpp/resolve/main/ggml-medium-q5_0.bin
echo Save to: models\ggml-medium-q5_0.bin
pause
exit /b 1
)
echo.
)
echo All prerequisites OK!
echo.
echo ============================================================
echo Starting pipeline...
echo ============================================================
echo.
:: ============================================================
:: STEP 1: VENV + DEPENDENCIES
:: ============================================================
if not exist ".venv\Scripts\python.exe" (
echo [1/4] Creating Python virtual environment...
python -m venv .venv
if errorlevel 1 (
echo ERROR: Failed to create venv.
pause
exit /b 1
)
echo Done.
) else (
echo [1/4] Virtual environment already exists.
)
echo [2/4] Installing Python dependencies...
.venv\Scripts\pip install -q -r requirements.txt
if errorlevel 1 (
echo ERROR: Failed to install dependencies.
pause
exit /b 1
)
echo Done.
:: ============================================================
:: STEP 2: DOWNLOAD
:: ============================================================
echo.
echo [3/4] Downloading audio files...
echo ============================================================
.venv\Scripts\python download.py
if errorlevel 1 (
echo.
echo WARNING: Some downloads failed. Check download_errors.log
echo Press any key to continue to transcription anyway, or Ctrl+C to abort.
pause >nul
)
:: ============================================================
:: STEP 3: TRANSCRIBE
:: ============================================================
echo.
echo [4/4] Transcribing with whisper.cpp...
echo ============================================================
echo Using: %WHISPER_BIN%
echo Model: %WHISPER_MODEL%
echo.
if "%~1"=="" (
.venv\Scripts\python transcribe.py
) else (
echo Modules filter: %~1
.venv\Scripts\python transcribe.py --modules %~1
)
if errorlevel 1 (
echo.
echo WARNING: Some transcriptions failed. Check transcribe_errors.log
)
:: ============================================================
:: DONE
:: ============================================================
echo.
echo ============================================================
echo Pipeline complete!
echo - Audio files: audio\
echo - Transcripts: transcripts\
echo - Manifest: manifest.json
echo.
echo Next step: generate summaries from WSL2 with Claude Code
echo python summarize.py
echo ============================================================
pause

51
setup_whisper.py
View File

@@ -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