lashman/whisper_voice
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity

Fix typography and wording in README, build spec, main

Browse Source
This commit is contained in:
lashman
2026-03-13 17:31:37 +02:00
parent 8ee67e9ef3
commit e86fab07d1
2 changed files with 158 additions and 96 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
build.spec
View File

@@ -8,6 +8,7 @@
# NO heavy dependencies (torch, PySide6, etc.) are bundled.
import os
import sys
import glob
block_cipher = None
@@ -61,7 +62,7 @@ a = Analysis(
'psutil', 'pynvml', 'pystray', 'PIL', 'Pillow',
'darkdetect', 'huggingface_hub', 'requests',
'tqdm', 'onnxruntime', 'av',
'tkinter', 'matplotlib', 'notebook', 'IPython',
'matplotlib', 'notebook', 'IPython',
],
win_no_prefer_redirects=False,
win_private_assemblies=False,
@@ -91,5 +92,5 @@ exe = EXE(
target_arch=None,
codesign_identity=None,
entitlements_file=None,
icon='assets/icon.ico',
icon='assets/icon.ico' if sys.platform == 'win32' else None,
)

249
main.py
View File

@@ -9,6 +9,14 @@ app_dir = os.path.dirname(os.path.abspath(__file__))
if app_dir not in sys.path:
sys.path.insert(0, app_dir)
# -----------------------------------------------------------------------------
# LINUX: Force XWayland (X11) for reliable window positioning & overlay behavior.
# Our input stack (evdev, UInput, wl-copy) is compositor-agnostic so this is safe.
# Native Wayland lacks app-controlled window positioning which the overlay needs.
# -----------------------------------------------------------------------------
if sys.platform == 'linux' and os.environ.get('WAYLAND_DISPLAY'):
os.environ.setdefault('QT_QPA_PLATFORM', 'xcb')
# -----------------------------------------------------------------------------
# WINDOWS DLL FIX (CRITICAL for Portable CUDA)
# Python 3.8+ on Windows requires explicit DLL directory addition.
@@ -16,20 +24,32 @@ if app_dir not in sys.path:
if os.name == 'nt' and hasattr(os, 'add_dll_directory'):
try:
from pathlib import Path
# Scan sys.path for site-packages
_candidate_dirs = set()
# 1. From sys.path (scan ALL site-packages, not just the first)
for p in sys.path:
path_obj = Path(p)
if path_obj.name == 'site-packages' and path_obj.exists():
nvidia_path = path_obj / "nvidia"
if nvidia_path.exists():
for subdir in nvidia_path.iterdir():
# Add 'bin' folder from each nvidia stub (cublas, cudnn, etc.)
bin_path = subdir / "bin"
if bin_path.exists():
os.add_dll_directory(str(bin_path))
# Also try adding site-packages itself just in case
# os.add_dll_directory(str(path_obj))
break
_candidate_dirs.add(str(path_obj.resolve()))
# 2. Relative to the Python executable (critical for embedded Python)
_exe_dir = Path(sys.executable).parent
for _sp in [_exe_dir / "Lib" / "site-packages", _exe_dir / "lib" / "site-packages"]:
if _sp.exists():
_candidate_dirs.add(str(_sp.resolve()))
# 3. Scan all candidates for nvidia DLL directories
for _sp_str in _candidate_dirs:
nvidia_path = Path(_sp_str) / "nvidia"
if nvidia_path.exists():
for subdir in nvidia_path.iterdir():
bin_path = subdir / "bin"
if bin_path.exists():
os.add_dll_directory(str(bin_path))
# Also add to PATH as fallback - some libraries
# (e.g. CTranslate2) load DLLs lazily via LoadLibrary
# which may not respect os.add_dll_directory()
os.environ['PATH'] = str(bin_path) + os.pathsep + os.environ.get('PATH', '')
except Exception:
pass
# -----------------------------------------------------------------------------
@@ -49,7 +69,8 @@ from src.core.hotkey_manager import HotkeyManager
from src.core.config import ConfigManager
from src.utils.injector import InputInjector
from src.core.paths import get_models_path, get_bundle_path
from src.utils.window_hook import WindowHook
if os.name == 'nt':
from src.utils.window_hook import WindowHook
from PySide6.QtGui import QSurfaceFormat
@@ -63,37 +84,52 @@ os.environ["QT_ENABLE_HIGHDPI_SCALING"] = "1"
os.environ["QT_AUTOSCREENSCALEFACTOR"] = "1"
# Detect resolution without creating QApplication (Fixes crash)
try:
import ctypes
user32 = ctypes.windll.user32
# Get physical screen width (unscaled)
# SetProcessDPIAware is needed to get the true resolution
user32.SetProcessDPIAware()
width = user32.GetSystemMetrics(0)
# Base scale centers around 1920 width.
# At 3840 (4k), res_scale is 2.0. If we want it ~40% smaller, we multiply by 0.6 = 1.2
res_scale = (width / 1920)
if width >= 3840:
res_scale *= 0.6 # Make it significantly smaller at 4k as requested
os.environ["QT_SCALE_FACTOR"] = str(max(1.0, res_scale))
except:
pass
if os.name == 'nt':
try:
import ctypes
user32 = ctypes.windll.user32
# Get physical screen width (unscaled)
# SetProcessDPIAware is needed to get the true resolution
user32.SetProcessDPIAware()
width = user32.GetSystemMetrics(0)
# Base scale centers around 1920 width.
# At 3840 (4k), res_scale is 2.0. If we want it ~40% smaller, we multiply by 0.6 = 1.2
res_scale = (width / 1920)
if width >= 3840:
res_scale *= 0.6 # Make it significantly smaller at 4k as requested
# Detect Windows "Reduce Motion" preference
try:
import ctypes
SPI_GETCLIENTAREAANIMATION = 0x1042
animation_enabled = ctypes.c_bool(True)
ctypes.windll.user32.SystemParametersInfoW(
SPI_GETCLIENTAREAANIMATION, 0,
ctypes.byref(animation_enabled), 0
)
if not animation_enabled.value:
ConfigManager().data["reduce_motion"] = True
ConfigManager().save()
except Exception:
pass
os.environ["QT_SCALE_FACTOR"] = str(max(1.0, res_scale))
except:
pass
# On Linux, Qt handles DPI automatically via QT_ENABLE_HIGHDPI_SCALING
# Detect "Reduce Motion" preference
if os.name == 'nt':
try:
import ctypes
SPI_GETCLIENTAREAANIMATION = 0x1042
animation_enabled = ctypes.c_bool(True)
ctypes.windll.user32.SystemParametersInfoW(
SPI_GETCLIENTAREAANIMATION, 0,
ctypes.byref(animation_enabled), 0
)
if not animation_enabled.value:
ConfigManager().data["reduce_motion"] = True
ConfigManager().save()
except Exception:
pass
elif sys.platform == 'linux':
try:
import subprocess as _sp
result = _sp.run(
['gsettings', 'get', 'org.gnome.desktop.interface', 'enable-animations'],
capture_output=True, text=True, timeout=2
)
if result.stdout.strip() == 'false':
ConfigManager().data["reduce_motion"] = True
ConfigManager().save()
except Exception:
pass
# Configure Logging
class QmlLoggingHandler(logging.Handler, QObject):
@@ -140,23 +176,33 @@ class DownloadWorker(QThread):
def run(self):
try:
import requests
from tqdm import tqdm
import shutil
model_path = get_models_path()
# Determine what to download
dest_dir = model_path / f"faster-whisper-{self.model_name}"
repo_id = f"Systran/faster-whisper-{self.model_name}"
files = ["config.json", "model.bin", "tokenizer.json", "vocabulary.json"]
required_files = ["config.json", "model.bin", "tokenizer.json", "vocabulary.json"]
base_url = f"https://huggingface.co/{repo_id}/resolve/main"
dest_dir.mkdir(parents=True, exist_ok=True)
# Skip if already complete
if dest_dir.exists() and all((dest_dir / f).exists() for f in required_files):
logging.info(f"Model {self.model_name} already downloaded.")
self.finished.emit()
return
# Download to a temp dir first, move on success
tmp_dir = model_path / f".tmp-faster-whisper-{self.model_name}"
if tmp_dir.exists():
shutil.rmtree(tmp_dir)
tmp_dir.mkdir(parents=True, exist_ok=True)
logging.info(f"Downloading {self.model_name} to {dest_dir}...")
# 1. Calculate Total Size
total_size = 0
file_sizes = {}
with requests.Session() as s:
for fname in files:
for fname in required_files:
url = f"{base_url}/{fname}"
head = s.head(url, allow_redirects=True)
if head.status_code == 200:
@@ -164,42 +210,48 @@ class DownloadWorker(QThread):
file_sizes[fname] = size
total_size += size
else:
# Fallback for vocabulary.json vs vocabulary.txt
if fname == "vocabulary.json":
# Try .txt? Or just skip if not found?
# Faster-whisper usually has vocabulary.json
pass
logging.warning(f"HEAD failed for {fname}: HTTP {head.status_code}")
# Abort if any required file is unavailable
missing = [f for f in required_files if f not in file_sizes]
if missing:
shutil.rmtree(tmp_dir, ignore_errors=True)
raise RuntimeError(f"Required model files unavailable: {missing}")
# 2. Download loop
downloaded_bytes = 0
with requests.Session() as s:
for fname in files:
if fname not in file_sizes: continue
for fname in required_files:
url = f"{base_url}/{fname}"
dest_file = dest_dir / fname
# Resume check?
# Simpler to just overwrite for reliability unless we want complex resume logic.
# We'll overwrite.
dest_file = tmp_dir / fname
resp = s.get(url, stream=True)
resp.raise_for_status()
with open(dest_file, 'wb') as f:
for chunk in resp.iter_content(chunk_size=8192):
if chunk:
f.write(chunk)
downloaded_bytes += len(chunk)
# Emit Progress
if total_size > 0:
pct = int((downloaded_bytes / total_size) * 100)
self.progress.emit(pct)
# 3. Validate all files present and non-empty
for fname in required_files:
fpath = tmp_dir / fname
if not fpath.exists() or fpath.stat().st_size == 0:
shutil.rmtree(tmp_dir, ignore_errors=True)
raise RuntimeError(f"Download incomplete: {fname} missing or empty")
# 4. Atomic move: replace dest with completed download
if dest_dir.exists():
shutil.rmtree(dest_dir)
tmp_dir.rename(dest_dir)
self.finished.emit()
except Exception as e:
logging.error(f"Download failed: {e}")
self.error.emit(str(e))
@@ -311,7 +363,8 @@ class WhisperApp(QObject):
self.bridge.llmDownloadRequested.connect(self.on_llm_download_requested)
self.engine.rootContext().setContextProperty("ui", self.bridge)
self.engine.rootContext().setContextProperty("isLinux", sys.platform == 'linux')
# 2. Tray setup
self.tray = SystemTray()
self.tray.quit_requested.connect(self.quit_app)
@@ -374,7 +427,7 @@ class WhisperApp(QObject):
self.overlay_root.setProperty("color", "transparent")
self.center_overlay()
# Preload Settings (Invisible)
logging.info("Preloading Settings window...")
self.open_settings()
@@ -382,23 +435,27 @@ class WhisperApp(QObject):
self.settings_root.setVisible(False)
# Install Low-Level Window Hook for Transparent Hit Test
try:
from src.utils.window_hook import WindowHook
hwnd = self.overlay_root.winId()
# Initial scale from config
scale = float(self.config.get("ui_scale"))
# Current Overlay Dimensions
win_w = int(460 * scale)
win_h = int(180 * scale)
self.window_hook = WindowHook(hwnd, win_w, win_h, initial_scale=scale)
self.window_hook.install()
# Initial state: Disabled because we start inactive
self.window_hook.set_enabled(False)
except Exception as e:
logging.error(f"Failed to install WindowHook: {e}")
if os.name == 'nt':
try:
from src.utils.window_hook import WindowHook
hwnd = self.overlay_root.winId()
# Initial scale from config
scale = float(self.config.get("ui_scale"))
# Current Overlay Dimensions
win_w = int(460 * scale)
win_h = int(180 * scale)
self.window_hook = WindowHook(hwnd, win_w, win_h, initial_scale=scale)
self.window_hook.install()
# Initial state: Disabled because we start inactive
self.window_hook.set_enabled(False)
except Exception as e:
logging.error(f"Failed to install WindowHook: {e}")
else:
# On Linux, use Qt flag for click-through overlay
self.overlay_root.setFlag(Qt.WindowTransparentForInput, True)
def center_overlay(self):
"""Calculates and sets the Overlay position above the taskbar."""
@@ -812,19 +869,23 @@ class WhisperApp(QObject):
self.bridge.update_status("Error")
logging.error(f"Download Error: {err}")
def _update_overlay_state(self, is_active):
"""Update overlay visibility and input handling based on active state."""
if hasattr(self, 'window_hook'):
self.window_hook.set_enabled(is_active)
elif sys.platform == 'linux' and self.overlay_root:
self.overlay_root.setFlag(Qt.WindowTransparentForInput, not is_active)
@Slot(bool)
def on_ui_toggle_request(self, is_recording):
"""Called when recording state changes."""
# Update Window Hook to allow clicking if active
is_active = is_recording or self.bridge.isProcessing
if hasattr(self, 'window_hook'):
self.window_hook.set_enabled(is_active)
self._update_overlay_state(is_active)
@Slot(bool)
def on_processing_changed(self, is_processing):
is_active = self.bridge.isRecording or is_processing
if hasattr(self, 'window_hook'):
self.window_hook.set_enabled(is_active)
self._update_overlay_state(is_active)
if __name__ == "__main__":
import sys