25 Commits
Author SHA1 Message Date
Deniz Şafak 6b3125b624 v1.2.2 2025-11-19 02:06:33 +03:00
Deniz Şafak bb5c4204de Reformat using black 2025-11-19 01:54:11 +03:00
Deniz Şafak 43f5589a9d Update changelog and images 2025-11-19 01:39:50 +03:00
Deniz Şafak 10d3f470e7 Add support for embedding cover images in M4B files and update documentation 2025-11-19 01:03:10 +03:00
Deniz ŞafakandGitHub c72c8e777c Update CHANGELOG 2025-11-18 15:27:09 +03:00
Deniz ŞafakandGitHub b51e094af1 Update CHANGELOG with subtitle audio generation details
Added detailed instructions for generating audio from subtitle files.
2025-11-18 15:24:44 +03:00
Deniz ŞafakandGitHub 04844997d5 Update README.md 2025-11-18 15:13:42 +03:00
Deniz ŞafakandGitHub 7835211a25 Update README.md 2025-11-18 15:07:38 +03:00
Deniz Şafak 6bb6fcb406 Add subtitle file voicing feature, improvements in code and documentation 2025-11-18 04:37:15 +03:00
Deniz ŞafakandGitHub ad8a6e520e Update WINDOWS_INSTALL.bat 2025-11-17 12:23:00 +03:00
Deniz Şafak fe22fe83b0 Possible fix for "CUDA is not available" issue, improvements in code and readme 2025-11-16 01:30:32 +03:00
Deniz Şafak afbd5203fe Fixed [WinError 1114] A dynamic link library (DLL) initialization routine failed, Potential fix for CUDA GPU is not available 2025-10-30 12:52:46 +03:00
Deniz ŞafakandGitHub 4b175c7cf2 Update PyTorch installation instructions for version 2.8.0 2025-10-30 12:07:19 +03:00
Deniz ŞafakandGitHub 334c0654ca Modify PyTorch installation for CUDA 12.8
Updated PyTorch installation commands to use version 2.8.0 with CUDA (12.8) support.
2025-10-30 12:06:24 +03:00
Deniz ŞafakandGitHub 42b7979585 Add libxcb-cursor0 and libgl1 to Dockerfile
Mentioned in #97
2025-10-30 02:16:04 +03:00
Deniz Şafak c994c2eeb0 v1.2.1 2025-10-28 02:48:06 +03:00
Deniz Şafak e4fe8122ff Fix book handler showing old cache when replace_single_newlines changed 2025-10-27 18:27:07 +03:00
Deniz Şafak 4cef65e70e Fix replace single newlines preview, remove unused imports 2025-10-27 18:15:28 +03:00
Deniz Şafak 24d5588f09 Improvements in code 2025-10-27 17:50:59 +03:00
Deniz Şafak 7883b8865b Fixed light theme slider colors in voice mixer 2025-10-27 17:43:54 +03:00
Deniz Şafak 47fe6341b4 Reformat using black 2025-10-27 17:26:54 +03:00
Deniz Şafak 9d2e8bed00 Added Open processed file and Open input file options for items in the queue manager 2025-10-27 17:24:23 +03:00
Deniz Şafak eedf347866 Upgraded Abogen's interface from PyQt5 to PyQt6, Added tooltip indicators in queue manager 2025-10-27 17:08:32 +03:00
Deniz Şafak 0d0d3b7871 Fixed subtitle word-count splitting logic for more accurate segmentation 2025-10-22 18:27:26 +03:00
Deniz Şafak f80c86b00d Added loading gif animation to book handler window 2025-10-22 01:21:55 +03:00
17 changed files with 2594 additions and 829 deletions
+20
View File
@@ -1,3 +1,23 @@
# 1.2.2
- **You can now voice your subtitle files!** Simply add `.srt`, `.ass` or `.vtt` files to generate timed audio. Alternatively, add a text file with timestamps in `HH:MM:SS` or `HH:MM:SS,ms` format to generate audio that matches the timestamps. See [here](https://github.com/denizsafak/abogen?tab=readme-ov-file#about-timestamp-based-text-files) for detailed instructions.
- New option: **"Use silent gaps between subtitles"**: Prevents unnecessary audio speed-up by letting speech continue into the silent gaps between subtitles.
- New option: **"Subtitle speed adjustment method"**: Choose how to speed up audio when needed:
- **TTS Regeneration (better quality):** Re-generates the audio at a faster speed for more natural sound.
- **FFmpeg Time-stretch (better speed):** Quickly speeds up the generated audio.
- Added support for embedding cover images in M4B files. Abogen now automatically extracts cover images from EPUB and PDF files. You can also manually specify a cover image using the `<<METADATA_COVER_PATH:path>>` tag in your text file. (To prevent MPV from showing the cover image, you can add `audio-display=no` to your MPV config file.)
- Fixed `[WinError 1114] A dynamic link library (DLL) initialization routine failed` error on Windows, pre-loading PyTorch DLLs before initializing PyQt6 to avoid DLL initialization errors, mentioned in #98 by @ephr0n.
- Potential fix for `CUDA GPU is not available` issue, by ensuring PyTorch is installed correctly with CUDA support on Windows using the installer script.
- Improvements in code and documentation.
# 1.2.1
- Upgraded Abogen's interface from PyQt5 to PyQt6 for better compatibility and long-term support.
- Added tooltip indicators in queue manager to display book handler options (`Save chapters separately` and `Merge chapters at the end`) for queued items.
- Added `Open processed file` and `Open input file` options for items in the queue manager, instead of just `Open file` option.
- Added loading gif animation to book handler window.
- Fixed light theme slider colors in voice mixer for better visibility (for non-Windows users).
- Fixed subtitle word-count splitting logic for more accurate segmentation.
- Improvements in code and documentation.
# 1.2.0
- Added `Line` option to subtitle generation modes, allowing subtitles to be generated based on line breaks in the text, by @mleg in #94.
- Added a loading indicator to the book handler window for better user experience during book preprocessing.
+42 -9
View File
@@ -9,7 +9,7 @@
<a href="https://trendshift.io/repositories/14433" target="_blank"><img src="https://trendshift.io/api/badge/repositories/14433" alt="denizsafak%2Fabogen | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a>
Abogen is a powerful text-to-speech conversion tool that makes it easy to turn ePub, PDF, text or markdown files into high-quality audio with matching subtitles in seconds. Use it for audiobooks, voiceovers for Instagram, YouTube, TikTok, or any project that needs natural-sounding text-to-speech, using [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M).
Abogen is a powerful text-to-speech conversion tool that makes it easy to turn ePub, PDF, text, markdown, or subtitle files into high-quality audio with matching subtitles in seconds. Use it for audiobooks, voiceovers for Instagram, YouTube, TikTok, or any project that needs natural-sounding text-to-speech, using [Kokoro-82M](https://huggingface.co/hexgrad/Kokoro-82M).
<img title="Abogen Main" src='https://raw.githubusercontent.com/denizsafak/abogen/refs/heads/main/demo/abogen.png' width="380"> <img title="Abogen Processing" src='https://raw.githubusercontent.com/denizsafak/abogen/refs/heads/main/demo/abogen2.png' width="380">
@@ -42,7 +42,8 @@ python -m venv venv
venv\Scripts\activate
# For NVIDIA GPUs:
pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
# We need to use an older version of PyTorch (2.8.0) until this issue is fixed: https://github.com/pytorch/pytorch/issues/166628
pip install torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128
# For AMD GPUs:
# Not supported yet, because ROCm is not available on Windows. Use Linux if you have AMD GPU.
@@ -114,7 +115,7 @@ abogen
> If you installed Abogen using the Windows installer `(WINDOWS_INSTALL.bat)`, It should have created a shortcut in the same folder, or your desktop. You can run it from there. If you lost the shortcut, Abogen is located in `python_embedded/Scripts/abogen.exe`. You can run it from there directly.
## `How to use?`
1) Drag and drop any ePub, PDF, text or markdown file (or use the built-in text editor)
1) Drag and drop any ePub, PDF, text, markdown, or subtitle file (or use the built-in text editor)
2) Configure the settings:
- Set speech speed
- Select a voice (or create a custom voice using voice mixer)
@@ -132,7 +133,7 @@ Heres Abogen in action: in this demo, it processes 3,000 characters of tex
| Options | Description |
|---------|-------------|
| **Input Box** | Drag and drop `ePub`, `PDF`, `.TXT` or `.MD` files (or use built-in text editor) |
| **Input Box** | Drag and drop `ePub`, `PDF`, `.TXT`, `.MD`, `.SRT`, `.ASS` or `.VTT` files (or use built-in text editor) |
| **Queue options** | Add multiple files to a queue and process them in batch, with individual settings for each file. See [Queue mode](#queue-mode) for more details. |
| **Speed** | Adjust speech rate from `0.1x` to `2.0x` |
| **Select Voice** | First letter of the language code (e.g., `a` for American English, `b` for British English, etc.), second letter is for `m` for male and `f` for female. |
@@ -168,6 +169,8 @@ Heres Abogen in action: in this demo, it processes 3,000 characters of tex
| **Open config directory** | Opens the directory where the configuration file is stored. |
| **Open cache directory** | Opens the cache directory where converted text files are stored. |
| **Clear cache files** | Deletes cache files created during the conversion or preview. |
| **Use silent gaps between subtitles** | Prevents unnecessary audio speed-up by letting speech continue into the silent gaps between subtitle etries. In short, it ignores the end times in subtitle entries and uses the silent space until the beginning of the next subtitle entry. When disabled, it speeds up the audio to fit the exact time interval specified in the subtitle. (for subtitle files). |
| **Subtitle speed adjustment method** | Choose how to speed up audio when needed: `TTS Regeneration (better quality)` re-generates the audio at a faster speed, while `FFmpeg Time-stretch (better speed)` quickly speeds up the generated audio. (for subtitle files). |
| **Check for updates at startup** | Automatically checks for updates when the program starts. |
| **Disable Kokoro's internet access** | Prevents Kokoro from downloading models or voices from HuggingFace Hub, useful for offline use. |
| **Reset to default settings** | Resets all settings to their default values. |
@@ -227,7 +230,30 @@ Similar to chapter markers, it is possible to add metadata tags for `M4B` files.
<<METADATA_ALBUM_ARTIST:Album Artist>>
<<METADATA_COMPOSER:Narrator>>
<<METADATA_GENRE:Audiobook>>
<<METADATA_COVER_PATH:path/to/cover.jpg>>
```
> Note: `METADATA_COVER_PATH` is used to embed a cover image into the generated M4B file. Abogen automatically extracts the cover from EPUB and PDF files and adds this tag for you.
## `About Timestamp-based Text Files`
Similar to converting subtitle files to audio, Abogen can automatically detect text files that contain timestamps in `HH:MM:SS` or `HH:MM:SS,ms` format. When timestamps are found inside your text file, Abogen will ask if you want to use them for audio timing. This is useful for creating timed narrations, scripts, or transcripts where you need exact control over when each segment is spoken.
Format your text file like this:
```
00:00:00
This is the first segment of text.
00:00:15
This is the second segment, starting at 15 seconds.
00:00:45
And this is the third segment, starting at 45 seconds.
```
**Important notes:**
- Timestamps must be in `HH:MM:SS` or `HH:MM:SS,ms` format (e.g., `00:05:30` for 5 minutes 30 seconds, or `00:05:30,500` for 5 minutes 30.5 seconds)
- Milliseconds are optional and provide precision up to 1/1000th of a second
- Text before the first timestamp (if any) will automatically start at `00:00:00`
- When using timestamps, the subtitle generation mode setting is ignored
## `Supported Languages`
```
@@ -250,6 +276,7 @@ I highly recommend using [MPV](https://mpv.io/installation/) to play your audio
# --- MPV Settings ---
save-position-on-quit
keep-open=yes
audio-display=no
# --- Subtitle ---
sub-ass-override=no
sub-margin-y=50
@@ -345,14 +372,20 @@ This will start Abogen in command-line mode and display detailed error messages.
<a name="cuda-warning">How to fix "CUDA GPU is not available. Using CPU" warning?</a>
</b></summary>
> This message means PyTorch couldn't use your GPU. On Windows, Abogen supports NVIDIA GPUs with CUDA. AMD GPUs are supported only on Linux. Abogen will still run on the CPU, but it will be slower.
> This message means PyTorch could not use your GPU and has fallen back to the CPU. On Windows, Abogen only supports NVIDIA GPUs with CUDA. AMD GPUs are not supported on Windows (they are only supported on Linux with ROCm). Abogen will still work on the CPU, but processing will be slower compared to a supported GPU.
>
> If you have a compatible NVIDIA GPU on Windows and still see this warning:
> Open your terminal in the Abogen folder (the folder that contains `python_embedded`) and type:
> ```bash
> python_embedded\python.exe -m pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu128
> python_embedded\python.exe -m pip install --force-reinstall torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128
> ```
> If you have an AMD GPU, use Linux and follow the Linux/ROCm [instructions](#how-to-install-). If you want to keep running on CPU, no action is required, but performance will just be reduced. See [#32](https://github.com/denizsafak/abogen/issues/32) for more details.
>
> If this does not resolve the issue and you are using an older NVIDIA GPU that does not support CUDA 12.8, you can try installing an older version of PyTorch that supports your GPU. For example, for CUDA 12.6, run:
> ```bash
> python_embedded\python.exe -m pip install --force-reinstall torch==2.8.0+cu126 torchvision==0.23.0+cu126 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu126
> ```
>
> If you have an AMD GPU, you need to use Linux and follow the Linux/ROCm [instructions](#linux). If you want to keep running on CPU, no action is required, but performance will just be reduced. See [#32](https://github.com/denizsafak/abogen/issues/32) for more details.
</details>
@@ -382,7 +415,7 @@ This will start Abogen in command-line mode and display detailed error messages.
> I faced this error when trying to run Abogen in a virtual Windows machine without GPU support. Here's how I fixed it:
> If you installed Abogen using the Windows installer `(WINDOWS_INSTALL.bat)`, go to Abogen's folder (that contains `python_embedded`), open your terminal there and run:
> ```bash
> python_embedded\python.exe -m pip install torch==2.8.0 torchaudio==2.8.0 torchvision==0.23.0
> python_embedded\python.exe -m pip install --force-reinstall torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128
> ```
> If you installed Abogen using pip, open your terminal in the virtual environment and run:
> ```bash
@@ -458,4 +491,4 @@ This project is available under the MIT License - see the [LICENSE](https://gith
> [!IMPORTANT]
> Subtitle generation currently works only for English. This is because Kokoro provides timestamp tokens only for English text. If you want subtitles in other languages, please request this feature in the [Kokoro project](https://github.com/hexgrad/kokoro). For more technical details, see [this line](https://github.com/hexgrad/kokoro/blob/6d87f4ae7abc2d14dbc4b3ef2e5f19852e861ac2/kokoro/pipeline.py#L383) in the Kokoro's code.
> Tags: audiobook, kokoro, text-to-speech, TTS, audiobook generator, audiobooks, text to speech, audiobook maker, audiobook creator, audiobook generator, voice-synthesis, text to audio, text to audio converter, text to speech converter, text to speech generator, text to speech software, text to speech app, epub to audio, pdf to audio, markdown to audio, content-creation, media-generation
> Tags: audiobook, kokoro, text-to-speech, TTS, audiobook generator, audiobooks, text to speech, audiobook maker, audiobook creator, audiobook generator, voice-synthesis, text to audio, text to audio converter, text to speech converter, text to speech generator, text to speech software, text to speech app, epub to audio, pdf to audio, markdown to audio, subtitle to audio, srt to audio, ass to audio, vtt to audio, webvtt to audio, content-creation, media-generation
+8 -7
View File
@@ -8,9 +8,6 @@ cd /d "%~dp0"
:: Japanese: "ja"
set MISAKI_LANG=en
:: Set PyTorch CUDA version
set CUDA_VERSION=128
:::
::: _ ____ ___ ____ _____ _ _
::: / \ | __ ) / _ \ / ___|| ____| \ | |
@@ -281,8 +278,10 @@ if /I "%IS_NVIDIA%"=="true" (
for /f %%i in ('%PYTHON_CONSOLE_PATH% -c "from torch.cuda import is_available; print(is_available())"') do set cuda_available=%%i
if "%cuda_available%"=="False" (
echo Installing PyTorch with CUDA %CUDA_VERSION% support...
%PYTHON_CONSOLE_PATH% -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu%CUDA_VERSION% --no-warn-script-location
echo Installing PyTorch with CUDA (12.8) support...
:: We need to use an older version of PyTorch (2.8.0) until this issue is fixed: https://github.com/pytorch/pytorch/issues/166628
:: Solution mentioned by @mazenemam19 in #99:
%PYTHON_CONSOLE_PATH% -m pip install torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128 --no-warn-script-location
echo.
if errorlevel 1 (
echo Failed to install PyTorch.
@@ -305,8 +304,10 @@ if /I "%IS_NVIDIA%"=="true" (
if errorlevel 2 (
echo Skipping PyTorch installation.
) else (
echo Installing PyTorch with CUDA %CUDA_VERSION% support...
%PYTHON_CONSOLE_PATH% -m pip install torch torchvision torchaudio --extra-index-url https://download.pytorch.org/whl/cu%CUDA_VERSION% --no-warn-script-location
echo Installing PyTorch with CUDA (12.8) support...
:: We need to use an older version of PyTorch (2.8.0) until this issue is fixed: https://github.com/pytorch/pytorch/issues/166628
:: Solution mentioned by @mazenemam19 in #99:
%PYTHON_CONSOLE_PATH% -m pip install torch==2.8.0+cu128 torchvision==0.23.0+cu128 torchaudio==2.8.0 --index-url https://download.pytorch.org/whl/cu128 --no-warn-script-location
if errorlevel 1 (
echo Failed to install PyTorch.
pause
+3 -1
View File
@@ -12,8 +12,10 @@ RUN apt-get update \
python3 \
python3-venv \
python3-pip \
python3-pyqt5 \
python3-pyqt6 \
espeak-ng \
libxcb-cursor0 \
libgl1 \
&& apt-get clean \
&& rm -rf /var/lib/apt/lists/*
+1 -1
View File
@@ -1 +1 @@
1.2.0
1.2.2
+424 -259
View File
File diff suppressed because it is too large Load Diff
+6 -3
View File
@@ -2,9 +2,7 @@ from abogen.utils import get_version
# Program Information
PROGRAM_NAME = "abogen"
PROGRAM_DESCRIPTION = (
"Generate audiobooks from EPUBs, PDFs and text with synchronized captions."
)
PROGRAM_DESCRIPTION = "Generate audiobooks from EPUBs, PDFs, text and subtitles with synchronized captions."
GITHUB_URL = "https://github.com/denizsafak/abogen"
VERSION = get_version()
@@ -44,6 +42,7 @@ SUPPORTED_SOUND_FORMATS = [
SUPPORTED_SUBTITLE_FORMATS = [
"srt",
"ass",
"vtt",
]
# Supported input formats
@@ -51,6 +50,9 @@ SUPPORTED_INPUT_FORMATS = [
"epub",
"pdf",
"txt",
"srt",
"ass",
"vtt",
]
# Supported languages for subtitle generation
@@ -148,6 +150,7 @@ COLORS = {
"BLUE_BORDER_HOVER": "#6ab0de",
"YELLOW_BACKGROUND": "rgba(255, 221, 51, 0.40)",
"GREY_BACKGROUND": "rgba(128, 128, 128, 0.15)",
"GREY_BORDER": "#808080",
"RED_BACKGROUND": "rgba(232, 78, 60, 0.15)",
"RED_BG": "rgba(232, 78, 60, 0.10)",
"RED_BG_HOVER": "rgba(232, 78, 60, 0.15)",
+1196 -142
View File
File diff suppressed because it is too large Load Diff
+426 -205
View File
File diff suppressed because it is too large Load Diff
+38 -10
View File
@@ -1,39 +1,65 @@
from json import load
import os
import sys
import platform
import atexit
import signal
# Fix PyTorch DLL loading issue ([WinError 1114]) on Windows before importing PyQt6
if platform.system() == "Windows":
import ctypes
from importlib.util import find_spec
try:
if (
(spec := find_spec("torch"))
and spec.origin
and os.path.exists(
dll_path := os.path.join(os.path.dirname(spec.origin), "lib", "c10.dll")
)
):
ctypes.CDLL(os.path.normpath(dll_path))
except Exception:
pass
# Qt platform plugin detection (fixes #59)
try:
from PyQt5.QtCore import QLibraryInfo
plugins = QLibraryInfo.location(QLibraryInfo.PluginsPath)
from PyQt6.QtCore import QLibraryInfo
# Get the path to the plugins directory
plugins = QLibraryInfo.path(QLibraryInfo.LibraryPath.PluginsPath)
# Normalize path to use the OS-native separators and absolute path
platform_dir = os.path.normpath(os.path.join(plugins, "platforms"))
# Ensure we work with an absolute path for clarity
platform_dir = os.path.abspath(platform_dir)
if os.path.isdir(platform_dir):
os.environ["QT_QPA_PLATFORM_PLUGIN_PATH"] = platform_dir
print("QT_QPA_PLATFORM_PLUGIN_PATH set to:", platform_dir)
else:
print("PyQt5 platform plugins not found at", platform_dir)
print("PyQt6 platform plugins not found at", platform_dir)
except ImportError:
print("PyQt5 not installed.")
print("PyQt6 not installed.")
# Set application ID for Windows taskbar icon
if platform.system() == "Windows":
try:
from abogen.constants import PROGRAM_NAME, VERSION
import ctypes
app_id = f"{PROGRAM_NAME}.{VERSION}"
ctypes.windll.shell32.SetCurrentProcessExplicitAppUserModelID(app_id)
except Exception as e:
print("Warning: failed to set AppUserModelID:", e)
from PyQt5.QtWidgets import QApplication
from PyQt5.QtGui import QIcon
from PyQt5.QtCore import qInstallMessageHandler, QtMsgType
from PyQt6.QtWidgets import QApplication
from PyQt6.QtGui import QIcon
from PyQt6.QtCore import (
QLibraryInfo,
qInstallMessageHandler,
QtMsgType,
)
# Add the directory to Python path
sys.path.insert(0, os.path.join(os.path.dirname(__file__)))
@@ -82,10 +108,12 @@ if platform.system() == "Darwin" and platform.processor() == "arm":
# Custom message handler to filter out specific Qt warnings
def qt_message_handler(mode, context, message):
# In PyQt6, the mode is an enum, so we compare with the enum members
if "Wayland does not support QWindow::requestActivate()" in message:
return # Suppress this specific message
if "setGrabPopup called with a parent, QtWaylandClient" in message:
return
if mode == QtMsgType.QtWarningMsg:
print(f"Qt Warning: {message}")
elif mode == QtMsgType.QtCriticalMsg:
@@ -123,13 +151,13 @@ def main():
# Set the .desktop name on Linux
if platform.system() == "Linux":
try:
app.setDesktopFileName("abogen.desktop")
app.setDesktopFileName("abogen")
except AttributeError:
pass
ex = abogen()
ex.show()
sys.exit(app.exec_())
sys.exit(app.exec())
if __name__ == "__main__":
+265 -112
View File
@@ -2,7 +2,7 @@
# button to remove an item from the queue
# button to clear the queue
from PyQt5.QtWidgets import (
from PyQt6.QtWidgets import (
QDialog,
QVBoxLayout,
QHBoxLayout,
@@ -14,18 +14,20 @@ from PyQt5.QtWidgets import (
QLabel,
QWidget,
QSizePolicy,
QAbstractItemView,
)
from PyQt5.QtCore import QFileInfo, Qt
from PyQt6.QtCore import QFileInfo, Qt
from abogen.constants import COLORS
from copy import deepcopy
from PyQt5.QtGui import QFontMetrics
from PyQt6.QtGui import QFontMetrics
class ElidedLabel(QLabel):
def __init__(self, text, parent=None):
super().__init__(text, parent)
def __init__(self, text):
super().__init__(text)
self._full_text = text
self.setSizePolicy(QSizePolicy.Expanding, QSizePolicy.Preferred)
self.setSizePolicy(QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Preferred)
self.setTextFormat(Qt.TextFormat.PlainText)
def setText(self, text):
self._full_text = text
@@ -34,7 +36,9 @@ class ElidedLabel(QLabel):
def resizeEvent(self, event):
metrics = QFontMetrics(self.font())
elided = metrics.elidedText(self._full_text, Qt.ElideRight, self.width())
elided = metrics.elidedText(
self._full_text, Qt.TextElideMode.ElideRight, self.width()
)
super().setText(elided)
super().resizeEvent(event)
@@ -53,8 +57,12 @@ class QueueListItemWidget(QWidget):
name_label = ElidedLabel(os.path.basename(file_name))
char_label = QLabel(f"Chars: {char_count}")
char_label.setStyleSheet(f"color: {COLORS['LIGHT_DISABLED']};")
char_label.setAlignment(Qt.AlignRight | Qt.AlignVCenter)
char_label.setSizePolicy(QSizePolicy.Minimum, QSizePolicy.Preferred)
char_label.setAlignment(
Qt.AlignmentFlag.AlignRight | Qt.AlignmentFlag.AlignVCenter
)
char_label.setSizePolicy(
QSizePolicy.Policy.Minimum, QSizePolicy.Policy.Preferred
)
layout.addWidget(name_label, 1)
layout.addWidget(char_label, 0)
self.setLayout(layout)
@@ -67,17 +75,23 @@ class DroppableQueueListWidget(QListWidget):
self.setAcceptDrops(True)
# Overlay for drag hover
self.drag_overlay = QLabel("", self)
self.drag_overlay.setAlignment(Qt.AlignCenter)
self.drag_overlay.setAlignment(Qt.AlignmentFlag.AlignCenter)
self.drag_overlay.setStyleSheet(
f"border:2px dashed {COLORS['BLUE_BORDER_HOVER']}; border-radius:5px; padding:20px; background:{COLORS['BLUE_BG_HOVER']};"
)
self.drag_overlay.setVisible(False)
self.drag_overlay.setAttribute(Qt.WA_TransparentForMouseEvents, True)
self.drag_overlay.setAttribute(
Qt.WidgetAttribute.WA_TransparentForMouseEvents, True
)
def dragEnterEvent(self, event):
if event.mimeData().hasUrls():
for url in event.mimeData().urls():
if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt"):
file_path = url.toLocalFile().lower()
if url.isLocalFile() and (
file_path.endswith(".txt")
or file_path.endswith((".srt", ".ass", ".vtt"))
):
self.drag_overlay.resize(self.size())
self.drag_overlay.setVisible(True)
event.acceptProposedAction()
@@ -88,7 +102,11 @@ class DroppableQueueListWidget(QListWidget):
def dragMoveEvent(self, event):
if event.mimeData().hasUrls():
for url in event.mimeData().urls():
if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt"):
file_path = url.toLocalFile().lower()
if url.isLocalFile() and (
file_path.endswith(".txt")
or file_path.endswith((".srt", ".ass", ".vtt"))
):
event.acceptProposedAction()
return
event.ignore()
@@ -103,7 +121,11 @@ class DroppableQueueListWidget(QListWidget):
file_paths = [
url.toLocalFile()
for url in event.mimeData().urls()
if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt")
if url.isLocalFile()
and (
url.toLocalFile().lower().endswith(".txt")
or url.toLocalFile().lower().endswith((".srt", ".ass", ".vtt"))
)
]
if file_paths:
self.parent_dialog.add_files_from_paths(file_paths)
@@ -132,34 +154,38 @@ class QueueManager(QDialog):
layout.setSpacing(12) # set spacing between widgets in main layout
# list of queued items
self.listwidget = DroppableQueueListWidget(self)
self.listwidget.setSelectionMode(QListWidget.ExtendedSelection)
self.listwidget.setSelectionMode(
QAbstractItemView.SelectionMode.ExtendedSelection
)
self.listwidget.setAlternatingRowColors(True)
self.listwidget.setContextMenuPolicy(Qt.CustomContextMenu)
self.listwidget.setContextMenuPolicy(Qt.ContextMenuPolicy.CustomContextMenu)
self.listwidget.customContextMenuRequested.connect(self.show_context_menu)
# Add informative instructions at the top
instructions = QLabel(
"<h2>How Queue Works?</h2>"
"You can add text files (.txt) directly using the '<b>Add files</b>' button below. "
"You can add text and subtitle files (.txt, .srt, .ass, .vtt) directly using the '<b>Add files</b>' button below. "
"To add PDF, EPUB or markdown files, use the input box in the main window and click the <b>'Add to Queue'</b> button. "
"Each file in the queue keeps the configuration settings active when it was added. "
"Changing the main window configuration afterward <b>does not</b> affect files already in the queue. "
"You can view each file's configuration by hovering over them."
)
instructions.setAlignment(Qt.AlignLeft)
instructions.setAlignment(Qt.AlignmentFlag.AlignLeft)
instructions.setWordWrap(True)
instructions.setStyleSheet("margin-bottom: 8px;")
layout.addWidget(instructions)
# Overlay label for empty queue
self.empty_overlay = QLabel(
"Drag and drop your text files here or use the 'Add files' button.",
"Drag and drop your text or subtitle files here or use the 'Add files' button.",
self.listwidget,
)
self.empty_overlay.setAlignment(Qt.AlignCenter)
self.empty_overlay.setAlignment(Qt.AlignmentFlag.AlignCenter)
self.empty_overlay.setStyleSheet(
f"color: {COLORS['LIGHT_DISABLED']}; background: transparent; padding: 20px;"
)
self.empty_overlay.setWordWrap(True)
self.empty_overlay.setAttribute(Qt.WA_TransparentForMouseEvents, True)
self.empty_overlay.setAttribute(
Qt.WidgetAttribute.WA_TransparentForMouseEvents, True
)
self.empty_overlay.hide()
# add queue items to the list
self.process_queue()
@@ -192,7 +218,10 @@ class QueueManager(QDialog):
self.listwidget.currentItemChanged.connect(self.update_button_states)
self.listwidget.itemSelectionChanged.connect(self.update_button_states)
buttons = QDialogButtonBox(QDialogButtonBox.Ok | QDialogButtonBox.Cancel, self)
buttons = QDialogButtonBox(
QDialogButtonBox.StandardButton.Ok | QDialogButtonBox.StandardButton.Cancel,
self,
)
buttons.accepted.connect(self.accept)
buttons.rejected.connect(self.reject)
@@ -208,10 +237,9 @@ class QueueManager(QDialog):
def process_queue(self):
"""Process the queue items."""
import os
self.listwidget.clear()
if not self.queue:
self.empty_overlay.resize(self.listwidget.size())
self.empty_overlay.show()
self.update_button_states()
return
@@ -222,11 +250,19 @@ class QueueManager(QDialog):
# Determine display file path (prefer save_base_path for original file)
display_file_path = getattr(item, "save_base_path", None) or item.file_name
processing_file_path = item.file_name
# Normalize paths for consistent display (fixes Windows path separator issues)
display_file_path = os.path.normpath(display_file_path) if display_file_path else display_file_path
processing_file_path = os.path.normpath(processing_file_path) if processing_file_path else processing_file_path
display_file_path = (
os.path.normpath(display_file_path)
if display_file_path
else display_file_path
)
processing_file_path = (
os.path.normpath(processing_file_path)
if processing_file_path
else processing_file_path
)
# Only show the file name, not the full path
display_name = display_file_path
@@ -240,13 +276,19 @@ class QueueManager(QDialog):
# For plain .txt inputs we don't need to show a separate processing file
show_processing = True
try:
if isinstance(display_file_path, str) and display_file_path.lower().endswith('.txt'):
if isinstance(
display_file_path, str
) and display_file_path.lower().endswith(".txt"):
show_processing = False
except Exception:
show_processing = True
tooltip = f"<b>Input File:</b> {display_file_path}<br>"
if show_processing and processing_file_path and processing_file_path != display_file_path:
if (
show_processing
and processing_file_path
and processing_file_path != display_file_path
):
tooltip += f"<b>Processing File:</b> {processing_file_path}<br>"
tooltip += (
f"<b>Language:</b> {getattr(item, 'lang_code', '')}<br>"
@@ -260,15 +302,28 @@ class QueueManager(QDialog):
f"<b>Subtitle Mode:</b> {getattr(item, 'subtitle_mode', '')}<br>"
f"<b>Output Format:</b> {getattr(item, 'output_format', '')}<br>"
f"<b>Characters:</b> {getattr(item, 'total_char_count', '')}<br>"
f"<b>Replace Single Newlines:</b> {getattr(item, 'replace_single_newlines', False)}"
f"<b>Replace Single Newlines:</b> {getattr(item, 'replace_single_newlines', False)}<br>"
f"<b>Use Silent Gaps:</b> {getattr(item, 'use_silent_gaps', False)}<br>"
f"<b>Speed Method:</b> {getattr(item, 'subtitle_speed_method', 'tts')}"
)
# Add book handler options if present
save_chapters_separately = getattr(item, "save_chapters_separately", None)
merge_chapters_at_end = getattr(item, "merge_chapters_at_end", None)
if save_chapters_separately is not None:
tooltip += f"<br><b>Save chapters separately:</b> {'Yes' if save_chapters_separately else 'No'}"
# Only show merge option if saving chapters separately
if save_chapters_separately and merge_chapters_at_end is not None:
tooltip += f"<br><b>Merge chapters at the end:</b> {'Yes' if merge_chapters_at_end else 'No'}"
list_item.setToolTip(tooltip)
list_item.setIcon(icon)
# Store both paths for context menu
list_item.setData(Qt.UserRole, {
'display_path': display_file_path,
'processing_path': processing_file_path
})
list_item.setData(
Qt.ItemDataRole.UserRole,
{
"display_path": display_file_path,
"processing_path": processing_file_path,
},
)
# Use custom widget for display
char_count = getattr(item, "total_char_count", 0)
widget = QueueListItemWidget(display_file_path, char_count)
@@ -280,7 +335,7 @@ class QueueManager(QDialog):
items = self.listwidget.selectedItems()
if not items:
return
from PyQt5.QtWidgets import QMessageBox
from PyQt6.QtWidgets import QMessageBox
# Remove by index to ensure correct mapping
rows = sorted([self.listwidget.row(item) for item in items], reverse=True)
@@ -290,10 +345,10 @@ class QueueManager(QDialog):
self,
"Confirm Remove",
f"Are you sure you want to remove {len(rows)} selected items from the queue?",
QMessageBox.Yes | QMessageBox.No,
QMessageBox.No,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
QMessageBox.StandardButton.No,
)
if reply != QMessageBox.Yes:
if reply != QMessageBox.StandardButton.Yes:
return
for row in rows:
if 0 <= row < len(self.queue):
@@ -302,17 +357,17 @@ class QueueManager(QDialog):
self.update_button_states()
def clear_queue(self):
from PyQt5.QtWidgets import QMessageBox
from PyQt6.QtWidgets import QMessageBox
if len(self.queue) > 1:
reply = QMessageBox.question(
self,
"Confirm Clear Queue",
f"Are you sure you want to clear {len(self.queue)} items from the queue?",
QMessageBox.Yes | QMessageBox.No,
QMessageBox.No,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
QMessageBox.StandardButton.No,
)
if reply != QMessageBox.Yes:
if reply != QMessageBox.StandardButton.Yes:
return
self.queue.clear()
self.listwidget.clear()
@@ -362,6 +417,19 @@ class QueueManager(QDialog):
attrs["replace_single_newlines"] = getattr(
parent, "replace_single_newlines", False
)
# use_silent_gaps
attrs["use_silent_gaps"] = getattr(parent, "use_silent_gaps", False)
# subtitle_speed_method
attrs["subtitle_speed_method"] = getattr(
parent, "subtitle_speed_method", "tts"
)
# book handler options
attrs["save_chapters_separately"] = getattr(
parent, "save_chapters_separately", None
)
attrs["merge_chapters_at_end"] = getattr(
parent, "merge_chapters_at_end", None
)
else:
# fallback: empty values
attrs = {
@@ -378,11 +446,13 @@ class QueueManager(QDialog):
"replace_single_newlines",
]
}
attrs["save_chapters_separately"] = None
attrs["merge_chapters_at_end"] = None
return attrs
def add_files_from_paths(self, file_paths):
from abogen.utils import calculate_text_length
from PyQt5.QtWidgets import QMessageBox
from PyQt6.QtWidgets import QMessageBox
import os
current_attrs = self.get_current_attributes()
@@ -394,9 +464,14 @@ class QueueManager(QDialog):
item = QueueItem()
item.file_name = file_path
item.save_base_path = file_path # For .txt files, processing and save paths are the same
item.save_base_path = (
file_path # For .txt files, processing and save paths are the same
)
for attr, value in current_attrs.items():
setattr(item, attr, value)
# Override subtitle_mode to "Disabled" for subtitle files
if file_path.lower().endswith((".srt", ".ass", ".vtt")):
item.subtitle_mode = "Disabled"
# Read file content and calculate total_char_count using calculate_text_length
try:
with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
@@ -428,8 +503,16 @@ class QueueManager(QDialog):
== getattr(item, "total_char_count", None)
and getattr(queued_item, "replace_single_newlines", False)
== getattr(item, "replace_single_newlines", False)
and getattr(queued_item, "use_silent_gaps", False)
== getattr(item, "use_silent_gaps", False)
and getattr(queued_item, "subtitle_speed_method", "tts")
== getattr(item, "subtitle_speed_method", "tts")
and getattr(queued_item, "save_base_path", None)
== getattr(item, "save_base_path", None)
and getattr(queued_item, "save_chapters_separately", None)
== getattr(item, "save_chapters_separately", None)
and getattr(queued_item, "merge_chapters_at_end", None)
== getattr(item, "merge_chapters_at_end", None)
):
is_duplicate = True
break
@@ -447,12 +530,15 @@ class QueueManager(QDialog):
self.update_button_states()
def add_more_files(self):
from PyQt5.QtWidgets import QFileDialog
from PyQt6.QtWidgets import QFileDialog
from abogen.utils import calculate_text_length # import the function
# Only allow .txt files
# Allow .txt, .srt, .ass, and .vtt files
files, _ = QFileDialog.getOpenFileNames(
self, "Select .txt files", "", "Text Files (*.txt)"
self,
"Select text or subtitle files",
"",
"Supported Files (*.txt *.srt *.ass *.vtt)",
)
if not files:
return
@@ -477,9 +563,9 @@ class QueueManager(QDialog):
self.clear_button.setEnabled(bool(self.queue))
def show_context_menu(self, pos):
from PyQt5.QtWidgets import QMenu, QAction
from PyQt5.QtGui import QDesktopServices
from PyQt5.QtCore import QUrl
from PyQt6.QtWidgets import QMenu
from PyQt6.QtGui import QAction, QDesktopServices
from PyQt6.QtCore import QUrl
import os
global_pos = self.listwidget.viewport().mapToGlobal(pos)
@@ -491,75 +577,129 @@ class QueueManager(QDialog):
remove_action.triggered.connect(self.remove_item)
menu.addAction(remove_action)
# Add Open file action
open_file_action = QAction("Open file", self)
def open_file():
from PyQt5.QtWidgets import QMessageBox
item = selected_items[0]
paths = item.data(Qt.UserRole)
if isinstance(paths, dict):
file_path = paths.get('display_path', paths.get('processing_path', ''))
else:
file_path = paths # Fallback for old format
# Find the queue item
for q in self.queue:
if (getattr(q, "save_base_path", None) == file_path or
q.file_name == file_path):
target_path = getattr(q, "save_base_path", None) or q.file_name
if not os.path.exists(target_path):
QMessageBox.warning(
self, "File Not Found", f"The file does not exist."
)
return
QDesktopServices.openUrl(QUrl.fromLocalFile(target_path))
break
open_file_action.triggered.connect(open_file)
menu.addAction(open_file_action)
# Add Go to folder action
# If the queued item represents a converted document (markdown, pdf, epub)
# show two actions: Go to processed file (the cached .txt) and Go to input file (original source)
# Get paths for determining if it's a document input
item = selected_items[0]
paths = item.data(Qt.UserRole)
paths = item.data(Qt.ItemDataRole.UserRole)
if isinstance(paths, dict):
display_path = paths.get('display_path', '')
processing_path = paths.get('processing_path', '')
display_path = paths.get("display_path", "")
processing_path = paths.get("processing_path", "")
else:
display_path = paths
processing_path = paths
doc_exts = ('.md', '.markdown', '.pdf', '.epub')
doc_exts = (".md", ".markdown", ".pdf", ".epub")
is_document_input = (
isinstance(display_path, str) and display_path.lower().endswith(doc_exts)
isinstance(display_path, str)
and display_path.lower().endswith(doc_exts)
) or (
isinstance(processing_path, str) and processing_path.lower().endswith(doc_exts)
isinstance(processing_path, str)
and processing_path.lower().endswith(doc_exts)
)
from PyQt5.QtWidgets import QMessageBox
# Add Open file action(s)
def open_file_by_path(path_label: str):
from PyQt6.QtWidgets import QMessageBox
p = display_path if path_label == "display" else processing_path
if not p:
QMessageBox.warning(
self, "File Not Found", "Path is not available."
)
return
# Find the queue item and resolve the target path
target_path = None
for q in self.queue:
if (
getattr(q, "save_base_path", None) == display_path
or q.file_name == display_path
):
if path_label == "display":
target_path = (
getattr(q, "save_base_path", None) or q.file_name
)
else:
target_path = q.file_name
break
if (
getattr(q, "save_base_path", None) == processing_path
or q.file_name == processing_path
):
if path_label == "display":
target_path = (
getattr(q, "save_base_path", None) or q.file_name
)
else:
target_path = q.file_name
break
# Fallback to the raw path if resolution failed
if not target_path:
target_path = p
if not os.path.exists(target_path):
QMessageBox.warning(
self, "File Not Found", f"The file does not exist."
)
return
QDesktopServices.openUrl(QUrl.fromLocalFile(target_path))
if is_document_input:
# For documents, show two open options
open_processed_action = QAction("Open processed file", self)
open_processed_action.triggered.connect(
lambda: open_file_by_path("processing")
)
menu.addAction(open_processed_action)
open_input_action = QAction("Open input file", self)
open_input_action.triggered.connect(
lambda: open_file_by_path("display")
)
menu.addAction(open_input_action)
else:
# For plain text files, show single open option
open_file_action = QAction("Open file", self)
open_file_action.triggered.connect(lambda: open_file_by_path("display"))
menu.addAction(open_file_action)
# Add Go to folder action
# If the queued item represents a converted document (markdown, pdf, epub)
# show two actions: Go to processed file (the cached .txt) and Go to input file (original source)
from PyQt6.QtWidgets import QMessageBox
def open_folder_for(path_label: str):
# path_label should be either 'display' or 'processing'
p = display_path if path_label == 'display' else processing_path
p = display_path if path_label == "display" else processing_path
if not p:
QMessageBox.warning(self, "File Not Found", "Path is not available.")
QMessageBox.warning(
self, "File Not Found", "Path is not available."
)
return
# If the stored path is the display path (original) but the actual file may be
# stored on the queue object differently, try to resolve via the queue entry.
target_path = None
for q in self.queue:
if getattr(q, 'save_base_path', None) == display_path or q.file_name == display_path:
if path_label == 'display':
target_path = getattr(q, 'save_base_path', None) or q.file_name
if (
getattr(q, "save_base_path", None) == display_path
or q.file_name == display_path
):
if path_label == "display":
target_path = (
getattr(q, "save_base_path", None) or q.file_name
)
else:
target_path = q.file_name
break
if getattr(q, 'save_base_path', None) == processing_path or q.file_name == processing_path:
if path_label == 'display':
target_path = getattr(q, 'save_base_path', None) or q.file_name
if (
getattr(q, "save_base_path", None) == processing_path
or q.file_name == processing_path
):
if path_label == "display":
target_path = (
getattr(q, "save_base_path", None) or q.file_name
)
else:
target_path = q.file_name
break
@@ -568,7 +708,11 @@ class QueueManager(QDialog):
target_path = p
if not os.path.exists(target_path):
QMessageBox.warning(self, "File Not Found", f"The file does not exist: {target_path}")
QMessageBox.warning(
self,
"File Not Found",
f"The file does not exist: {target_path}",
)
return
folder = os.path.dirname(target_path)
if os.path.exists(folder):
@@ -576,11 +720,13 @@ class QueueManager(QDialog):
if is_document_input:
processed_action = QAction("Go to processed file", self)
processed_action.triggered.connect(lambda: open_folder_for('processing'))
processed_action.triggered.connect(
lambda: open_folder_for("processing")
)
menu.addAction(processed_action)
input_action = QAction("Go to input file", self)
input_action.triggered.connect(lambda: open_folder_for('display'))
input_action.triggered.connect(lambda: open_folder_for("display"))
menu.addAction(input_action)
else:
# Default behavior for non-document inputs: single "Go to folder" action
@@ -588,15 +734,22 @@ class QueueManager(QDialog):
def go_to_folder():
item = selected_items[0]
paths = item.data(Qt.UserRole)
paths = item.data(Qt.ItemDataRole.UserRole)
if isinstance(paths, dict):
file_path = paths.get('display_path', paths.get('processing_path', ''))
file_path = paths.get(
"display_path", paths.get("processing_path", "")
)
else:
file_path = paths # Fallback for old format
# Find the queue item
for q in self.queue:
if (getattr(q, "save_base_path", None) == file_path or q.file_name == file_path):
target_path = getattr(q, "save_base_path", None) or q.file_name
if (
getattr(q, "save_base_path", None) == file_path
or q.file_name == file_path
):
target_path = (
getattr(q, "save_base_path", None) or q.file_name
)
if not os.path.exists(target_path):
QMessageBox.warning(
self, "File Not Found", f"The file does not exist."
@@ -618,7 +771,7 @@ class QueueManager(QDialog):
clear_action = QAction("Clear Queue", self)
clear_action.triggered.connect(self.clear_queue)
menu.addAction(clear_action)
menu.exec_(global_pos)
menu.exec(global_pos)
def accept(self):
# Accept: keep changes
@@ -626,7 +779,7 @@ class QueueManager(QDialog):
def reject(self):
# Cancel: restore original queue
from PyQt5.QtWidgets import QMessageBox
from PyQt6.QtWidgets import QMessageBox
# Warn if user changed a lot (e.g., more than 1 items difference)
original_count = len(self._original_queue)
@@ -636,19 +789,19 @@ class QueueManager(QDialog):
self,
"Confirm Cancel",
f"Are you sure you want to cancel and discard all changes?",
QMessageBox.Yes | QMessageBox.No,
QMessageBox.No,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
QMessageBox.StandardButton.No,
)
if reply != QMessageBox.Yes:
if reply != QMessageBox.StandardButton.Yes:
return
self.queue.clear()
self.queue.extend(deepcopy(self._original_queue))
super().reject()
def keyPressEvent(self, event):
from PyQt5.QtCore import Qt
from PyQt6.QtCore import Qt
if event.key() == Qt.Key_Delete:
if event.key() == Qt.Key.Key_Delete:
self.remove_item()
else:
super().keyPressEvent(event)
+4
View File
@@ -14,4 +14,8 @@ class QueuedItem:
output_format: str
total_char_count: int
replace_single_newlines: bool = False
use_silent_gaps: bool = False
subtitle_speed_method: str = "tts"
save_base_path: str = None
save_chapters_separately: bool = None
merge_chapters_at_end: bool = None
+11 -3
View File
@@ -14,6 +14,7 @@ warnings.filterwarnings("ignore")
def detect_encoding(file_path):
import chardet
import charset_normalizer
with open(file_path, "rb") as f:
raw_data = f.read()
detected_encoding = None
@@ -28,6 +29,7 @@ def detect_encoding(file_path):
encoding = detected_encoding if detected_encoding else "utf-8"
return encoding.lower()
def get_resource_path(package, resource):
"""
Get the path to a resource file, with fallback to local file system.
@@ -255,24 +257,30 @@ def calculate_text_length(text):
def get_gpu_acceleration(enabled):
"""
Check GPU acceleration availability.
Note: On Windows, torch DLLs must be pre-loaded in main.py before PyQt6
to avoid DLL initialization errors.
"""
try:
import torch
from torch.cuda import is_available as cuda_available
if not enabled:
return "GPU available but using CPU.", False
# Check for Apple Silicon MPS
if platform.system() == "Darwin" and platform.processor() == "arm":
if torch.backends.mps.is_available():
return "MPS GPU available and enabled.", True
else:
return "MPS GPU not available on Apple Silicon. Using CPU.", False
# Check for CUDA
if cuda_available():
return "CUDA GPU available and enabled.", True
# Gather CUDA diagnostic info if not available
try:
cuda_devices = torch.cuda.device_count()
+149 -76
View File
@@ -1,6 +1,6 @@
import json
import os
from PyQt5.QtWidgets import (
from PyQt6.QtWidgets import (
QDialog,
QVBoxLayout,
QCheckBox,
@@ -22,12 +22,11 @@ from PyQt5.QtWidgets import (
QFileDialog,
QSplitter,
QMenu,
QAction,
QComboBox,
QApplication,
QComboBox,
)
from PyQt5.QtCore import Qt, QTimer, QPoint, QRect, QSize
from PyQt5.QtGui import QPixmap, QIcon
from PyQt6.QtCore import Qt, QTimer, QPoint, QRect, QSize
from PyQt6.QtGui import QPixmap, QIcon, QAction
from abogen.constants import (
VOICES_INTERNAL,
SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
@@ -91,7 +90,7 @@ class FlowLayout(QLayout):
return len(self._item_list)
def expandingDirections(self):
return Qt.Orientations(Qt.Orientation(0))
return Qt.Orientation(0)
def hasHeightForWidth(self):
return True
@@ -132,10 +131,14 @@ class FlowLayout(QLayout):
for item in self._item_list:
style = self.parentWidget().style() if self.parentWidget() else QStyle()
layout_spacing_x = style.layoutSpacing(
QSizePolicy.PushButton, QSizePolicy.PushButton, Qt.Horizontal
QSizePolicy.ControlType.PushButton,
QSizePolicy.ControlType.PushButton,
Qt.Orientation.Horizontal,
)
layout_spacing_y = style.layoutSpacing(
QSizePolicy.PushButton, QSizePolicy.PushButton, Qt.Vertical
QSizePolicy.ControlType.PushButton,
QSizePolicy.ControlType.PushButton,
Qt.Orientation.Vertical,
)
space_x = spacing if spacing >= 0 else layout_spacing_x
space_y = spacing if spacing >= 0 else layout_spacing_y
@@ -163,7 +166,7 @@ class VoiceMixer(QWidget):
super().__init__()
self.voice_name = voice_name
self.setFixedWidth(VOICE_MIXER_WIDTH)
self.setSizePolicy(QSizePolicy.Expanding, QSizePolicy.Expanding)
self.setSizePolicy(QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Expanding)
# TODO Set CSS for rounded corners
# self.setObjectName("VoiceMixer")
@@ -173,7 +176,7 @@ class VoiceMixer(QWidget):
# Name label at the top
name = voice_name
layout.addWidget(QLabel(name), alignment=Qt.AlignCenter)
layout.addWidget(QLabel(name), alignment=Qt.AlignmentFlag.AlignCenter)
# Voice name label with gender icon
is_female = self.voice_name in VOICES_INTERNAL and self.voice_name[1] == "f"
@@ -181,7 +184,9 @@ class VoiceMixer(QWidget):
# Icons layout (flag and gender)
icons_layout = QHBoxLayout()
icons_layout.setSpacing(3)
icons_layout.setAlignment(Qt.AlignCenter) # Center the icons horizontally
icons_layout.setAlignment(
Qt.AlignmentFlag.AlignCenter
) # Center the icons horizontally
# Flag icon
flag_icon_path = get_resource_path(
@@ -194,11 +199,21 @@ class VoiceMixer(QWidget):
gender_label = QLabel()
flag_pixmap = QPixmap(flag_icon_path)
flag_label.setPixmap(
flag_pixmap.scaled(16, 16, Qt.KeepAspectRatio, Qt.SmoothTransformation)
flag_pixmap.scaled(
16,
16,
Qt.AspectRatioMode.KeepAspectRatio,
Qt.TransformationMode.SmoothTransformation,
)
)
gender_pixmap = QPixmap(gender_icon_path)
gender_label.setPixmap(
gender_pixmap.scaled(16, 16, Qt.KeepAspectRatio, Qt.SmoothTransformation)
gender_pixmap.scaled(
16,
16,
Qt.AspectRatioMode.KeepAspectRatio,
Qt.TransformationMode.SmoothTransformation,
)
)
icons_layout.addWidget(flag_label)
icons_layout.addWidget(gender_label)
@@ -210,7 +225,7 @@ class VoiceMixer(QWidget):
self.checkbox = QCheckBox()
self.checkbox.setChecked(initial_status)
self.checkbox.stateChanged.connect(self.toggle_inputs)
layout.addWidget(self.checkbox, alignment=Qt.AlignCenter)
layout.addWidget(self.checkbox, alignment=Qt.AlignmentFlag.AlignCenter)
# Spinbox and slider
self.spin_box = QDoubleSpinBox()
@@ -219,26 +234,16 @@ class VoiceMixer(QWidget):
self.spin_box.setDecimals(2)
self.spin_box.setValue(initial_weight)
self.slider = QSlider(Qt.Vertical)
self.slider = QSlider(Qt.Orientation.Vertical)
self.slider.setRange(0, 100)
self.slider.setValue(int(initial_weight * 100))
self.slider.setSizePolicy(QSizePolicy.Fixed, QSizePolicy.Expanding)
self.slider.setSizePolicy(
QSizePolicy.Policy.Fixed, QSizePolicy.Policy.Expanding
)
self.slider.setFixedWidth(SLIDER_WIDTH)
# Fix slider in Windows
if platform.system() == "Windows":
appstyle = QApplication.instance().style().objectName().lower()
if appstyle != "windowsvista":
# Set custom groove color for disabled state using COLORS["GREY_BACKGROUND"]
self.slider.setStyleSheet(
f"""
QSlider::groove:vertical:disabled {{
background: {COLORS.get("GREY_BACKGROUND")};
width: 4px;
border-radius: 4px;
}}
"""
)
# Apply slider styling after widget is added to window (see showEvent)
self._slider_style_applied = False
# Connect controls
self.slider.valueChanged.connect(lambda val: self.spin_box.setValue(val / 100))
@@ -249,23 +254,67 @@ class VoiceMixer(QWidget):
# Layout for slider and labels
slider_layout = QVBoxLayout()
slider_layout.addWidget(self.spin_box)
slider_layout.addWidget(QLabel("1", alignment=Qt.AlignCenter))
slider_layout.addWidget(QLabel("1", alignment=Qt.AlignmentFlag.AlignCenter))
slider_center_layout = QHBoxLayout()
slider_center_layout.addWidget(self.slider, alignment=Qt.AlignHCenter)
slider_center_layout.addWidget(
self.slider, alignment=Qt.AlignmentFlag.AlignHCenter
)
slider_center_layout.setContentsMargins(0, 0, 0, 0)
slider_center_widget = QWidget()
slider_center_widget.setLayout(slider_center_layout)
slider_layout.addWidget(slider_center_widget, stretch=1)
slider_layout.addWidget(QLabel("0", alignment=Qt.AlignCenter))
slider_layout.addWidget(QLabel("0", alignment=Qt.AlignmentFlag.AlignCenter))
slider_layout.setStretch(2, 1)
layout.addLayout(slider_layout, stretch=1)
self.setLayout(layout)
self.toggle_inputs()
def showEvent(self, event):
super().showEvent(event)
# Apply slider styling once when widget is shown and has access to parent
if not self._slider_style_applied:
self._slider_style_applied = True
# Fix slider in Windows
if platform.system() == "Windows":
appstyle = QApplication.instance().style().objectName().lower()
if appstyle != "windowsvista":
# Set custom groove color for disabled state using COLORS["GREY_BACKGROUND"]
self.slider.setStyleSheet(
f"""
QSlider::groove:vertical:disabled {{
background: {COLORS.get("GREY_BACKGROUND")};
width: 4px;
border-radius: 4px;
}}
"""
)
else:
# Apply same fix for Light theme on non-Windows systems
# Get theme from parent window's config
parent_window = self.window()
theme = "system"
while parent_window:
if hasattr(parent_window, "config"):
theme = parent_window.config.get("theme", "system")
break
parent_window = parent_window.parent()
if theme == "light":
self.slider.setStyleSheet(
f"""
QSlider::groove:vertical:disabled {{
background: {COLORS.get("GREY_BACKGROUND")};
width: 4px;
border-radius: 4px;
}}
"""
)
def toggle_inputs(self):
is_enabled = self.checkbox.isChecked()
self.spin_box.setEnabled(is_enabled)
@@ -307,9 +356,11 @@ class HoverLabel(QLabel):
"""
)
# Make sure the entire button is clickable, not just the text
self.delete_button.setFocusPolicy(Qt.NoFocus)
self.delete_button.setAttribute(Qt.WA_TransparentForMouseEvents, False)
self.delete_button.setCursor(Qt.PointingHandCursor)
self.delete_button.setFocusPolicy(Qt.FocusPolicy.NoFocus)
self.delete_button.setAttribute(
Qt.WidgetAttribute.WA_TransparentForMouseEvents, False
)
self.delete_button.setCursor(Qt.CursorShape.PointingHandCursor)
self.delete_button.hide()
def resizeEvent(self, event):
@@ -357,7 +408,7 @@ class VoiceFormulaDialog(QDialog):
if parent is not None and hasattr(parent, "subtitle_combo"):
self.subtitle_combo = parent.subtitle_combo
# Create main container layout with profile section and mixer section
splitter = QSplitter(Qt.Horizontal)
splitter = QSplitter(Qt.Orientation.Horizontal)
# Profile section
profile_widget = QWidget()
profile_layout = QVBoxLayout(profile_widget)
@@ -371,8 +422,8 @@ class VoiceFormulaDialog(QDialog):
profile_layout.addLayout(header_layout)
# Profile list
self.profile_list = QListWidget()
self.profile_list.setSelectionMode(QListWidget.SingleSelection)
self.profile_list.setSelectionBehavior(QListWidget.SelectRows)
self.profile_list.setSelectionMode(QListWidget.SelectionMode.SingleSelection)
self.profile_list.setSelectionBehavior(QListWidget.SelectionBehavior.SelectRows)
self.profile_list.setStyleSheet(
"QListWidget::item:selected { background: palette(highlight); color: palette(highlighted-text); }"
)
@@ -388,7 +439,7 @@ class VoiceFormulaDialog(QDialog):
idx = list(profiles.keys()).index(self.current_profile)
self.profile_list.setCurrentRow(idx)
profile_layout.addWidget(self.profile_list)
self.profile_list.setContextMenuPolicy(Qt.CustomContextMenu)
self.profile_list.setContextMenuPolicy(Qt.ContextMenuPolicy.CustomContextMenu)
self.profile_list.customContextMenuRequested.connect(
self.show_profile_context_menu
)
@@ -409,7 +460,9 @@ class VoiceFormulaDialog(QDialog):
self.setWindowTitle("Voice Mixer")
self.setWindowFlags(
Qt.Window | Qt.WindowCloseButtonHint | Qt.WindowMaximizeButtonHint
Qt.WindowType.Window
| Qt.WindowType.WindowCloseButtonHint
| Qt.WindowType.WindowMaximizeButtonHint
)
self.setMinimumSize(MIN_WINDOW_WIDTH, MIN_WINDOW_HEIGHT)
self.resize(INITIAL_WINDOW_WIDTH, INITIAL_WINDOW_HEIGHT)
@@ -468,21 +521,25 @@ class VoiceFormulaDialog(QDialog):
# Separator
separator = QFrame()
separator.setFrameShadow(QFrame.Sunken)
separator.setFrameShadow(QFrame.Shadow.Sunken)
mixer_layout.addWidget(separator)
# Voice list scroll area
self.scroll_area = QScrollArea()
self.scroll_area.setWidgetResizable(True)
self.scroll_area.setHorizontalScrollBarPolicy(Qt.ScrollBarAsNeeded)
self.scroll_area.setVerticalScrollBarPolicy(Qt.ScrollBarAsNeeded)
self.scroll_area.setHorizontalScrollBarPolicy(
Qt.ScrollBarPolicy.ScrollBarAsNeeded
)
self.scroll_area.setVerticalScrollBarPolicy(
Qt.ScrollBarPolicy.ScrollBarAsNeeded
)
self.scroll_area.viewport().installEventFilter(self)
self.voice_list_widget = QWidget()
self.voice_list_layout = QHBoxLayout()
self.voice_list_widget.setLayout(self.voice_list_layout)
self.voice_list_widget.setSizePolicy(
QSizePolicy.Expanding, QSizePolicy.Expanding
QSizePolicy.Policy.Expanding, QSizePolicy.Policy.Expanding
)
self.scroll_area.setWidget(self.voice_list_widget)
mixer_layout.addWidget(self.scroll_area, stretch=1)
@@ -497,6 +554,9 @@ class VoiceFormulaDialog(QDialog):
ok_button.setDefault(True)
ok_button.setFocus()
# Connect buttons
clear_all_button.clicked.connect(self.clear_all_voices)
ok_button.clicked.connect(self.accept)
# Connect buttons
clear_all_button.clicked.connect(self.clear_all_voices)
ok_button.clicked.connect(self.accept)
@@ -533,7 +593,7 @@ class VoiceFormulaDialog(QDialog):
def keyPressEvent(self, event):
# Bind Delete key to delete_profile when a profile is selected
if event.key() == Qt.Key_Delete and self.profile_list.hasFocus():
if event.key() == Qt.Key.Key_Delete and self.profile_list.hasFocus():
item = self.profile_list.currentItem()
if item:
self.delete_profile(item)
@@ -562,10 +622,12 @@ class VoiceFormulaDialog(QDialog):
self,
"Unsaved Changes",
msg,
QMessageBox.Save | QMessageBox.Discard | QMessageBox.Cancel,
QMessageBox.Save,
QMessageBox.StandardButton.Save
| QMessageBox.StandardButton.Discard
| QMessageBox.StandardButton.Cancel,
QMessageBox.StandardButton.Save,
)
if ret == QMessageBox.Save:
if ret == QMessageBox.StandardButton.Save:
# Save all using stored states
profiles = load_profiles()
for i in dirty_indices:
@@ -590,7 +652,7 @@ class VoiceFormulaDialog(QDialog):
self.update_profile_save_buttons()
self.update_profile_list_colors()
return True
elif ret == QMessageBox.Discard:
elif ret == QMessageBox.StandardButton.Discard:
# Discard all modifications
self._profile_states.clear()
for i in dirty_indices:
@@ -612,17 +674,19 @@ class VoiceFormulaDialog(QDialog):
else:
# Fallback to original logic for 0 or 1 dirty profile
box = QMessageBox(self)
box.setIcon(QMessageBox.Warning)
box.setIcon(QMessageBox.Icon.Warning)
box.setWindowTitle("Unsaved Changes")
box.setText(
"You have unsaved changes in your profile. Do you want to save the changes?"
)
box.setStandardButtons(
QMessageBox.Save | QMessageBox.Discard | QMessageBox.Cancel
QMessageBox.StandardButton.Save
| QMessageBox.StandardButton.Discard
| QMessageBox.StandardButton.Cancel
)
box.setDefaultButton(QMessageBox.Save)
ret = box.exec_()
if ret == QMessageBox.Save:
box.setDefaultButton(QMessageBox.StandardButton.Save)
ret = box.exec()
if ret == QMessageBox.StandardButton.Save:
for i in range(self.profile_list.count()):
item = self.profile_list.item(i)
name = item.text().lstrip("*")
@@ -636,7 +700,7 @@ class VoiceFormulaDialog(QDialog):
if hasattr(parent, "populate_profiles_in_voice_combo"):
parent.populate_profiles_in_voice_combo()
return True
elif ret == QMessageBox.Discard:
elif ret == QMessageBox.StandardButton.Discard:
profiles = load_profiles()
for i in range(self.profile_list.count()):
item = self.profile_list.item(i)
@@ -717,7 +781,7 @@ class VoiceFormulaDialog(QDialog):
return voice_mixer
def handle_voice_checkbox(self, voice_mixer, state):
if state == Qt.Checked:
if state == Qt.CheckState.Checked.value:
self.last_enabled_voice = voice_mixer.voice_name
self.update_weighted_sums()
@@ -767,7 +831,9 @@ class VoiceFormulaDialog(QDialog):
f'<b><span style="color:{COLORS.get("BLUE")}">{name}: {percentage:.1f}%</span></b>',
name,
)
voice_label.setSizePolicy(QSizePolicy.Preferred, QSizePolicy.Preferred)
voice_label.setSizePolicy(
QSizePolicy.Policy.Preferred, QSizePolicy.Policy.Preferred
)
voice_label.delete_button.clicked.connect(
lambda _, vn=name: self.disable_voice_by_name(vn)
)
@@ -787,7 +853,7 @@ class VoiceFormulaDialog(QDialog):
mixer.checkbox.setChecked(False)
def eventFilter(self, source, event):
if source is self.scroll_area.viewport() and event.type() == event.Wheel:
if source is self.scroll_area.viewport() and event.type() == event.Type.Wheel:
# Skip if over an enabled slider
if any(
mixer.slider.underMouse() and mixer.slider.isEnabled()
@@ -890,10 +956,10 @@ class VoiceFormulaDialog(QDialog):
self,
"Invalid Profiles",
msg,
QMessageBox.Yes | QMessageBox.Cancel,
QMessageBox.Yes,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.Cancel,
QMessageBox.StandardButton.Yes,
)
if reply == QMessageBox.Yes:
if reply == QMessageBox.StandardButton.Yes:
for i, name in reversed(zero):
self.profile_list.takeItem(i)
delete_profile(name)
@@ -980,8 +1046,8 @@ class VoiceFormulaDialog(QDialog):
super().closeEvent(event)
def _parse_rgba_to_qcolor(self, rgba_str):
from PyQt5.QtCore import Qt
from PyQt5.QtGui import QColor
from PyQt6.QtCore import Qt
from PyQt6.QtGui import QColor
"""Helper to convert 'rgba(R,G,B,A_float)' string to QColor."""
match = re.match(r"rgba\((\d+),\s*(\d+),\s*(\d+),\s*([\d.]+)\)", rgba_str)
@@ -1136,9 +1202,12 @@ class VoiceFormulaDialog(QDialog):
msg += f"\nThis will overwrite an existing profile."
msg += "\nContinue?"
reply = QMessageBox.question(
self, "Import Profile", msg, QMessageBox.Yes | QMessageBox.No
self,
"Import Profile",
msg,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
)
if reply != QMessageBox.Yes:
if reply != QMessageBox.StandardButton.Yes:
return
profiles.update(imported_profiles)
save_profiles(profiles)
@@ -1153,9 +1222,12 @@ class VoiceFormulaDialog(QDialog):
msg += f"\n{len(collisions)} profile(s) will be overwritten."
msg += "\nContinue?"
reply = QMessageBox.question(
self, "Import Profiles", msg, QMessageBox.Yes | QMessageBox.No
self,
"Import Profiles",
msg,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
)
if reply != QMessageBox.Yes:
if reply != QMessageBox.StandardButton.Yes:
return
profiles.update(imported_profiles)
save_profiles(profiles)
@@ -1196,7 +1268,7 @@ class VoiceFormulaDialog(QDialog):
menu.addAction(dup_act)
menu.addAction(export_act)
menu.addAction(delete_act)
act = menu.exec_(self.profile_list.viewport().mapToGlobal(pos))
act = menu.exec(self.profile_list.viewport().mapToGlobal(pos))
if act == rename_act:
self.rename_profile(item)
elif act == delete_act:
@@ -1323,9 +1395,9 @@ class VoiceFormulaDialog(QDialog):
self,
"Delete Profile",
f"Delete profile '{name}'?",
QMessageBox.Yes | QMessageBox.No,
QMessageBox.StandardButton.Yes | QMessageBox.StandardButton.No,
)
if reply == QMessageBox.Yes:
if reply == QMessageBox.StandardButton.Yes:
delete_profile(name)
row = self.profile_list.row(item)
self.profile_list.takeItem(row)
@@ -1378,7 +1450,7 @@ class VoiceFormulaDialog(QDialog):
self.profile_list.setItemWidget(item, widget)
def update_profile_list_colors(self):
from PyQt5.QtCore import Qt
from PyQt6.QtCore import Qt
profiles = load_profiles()
for i in range(self.profile_list.count()):
@@ -1386,13 +1458,14 @@ class VoiceFormulaDialog(QDialog):
name = item.text().lstrip("*")
if self._virtual_new_profile and name == "New profile":
color = self._parse_rgba_to_qcolor(COLORS.get("YELLOW_BACKGROUND"))
item.setData(Qt.BackgroundRole, color)
item.setData(Qt.ItemDataRole.BackgroundRole, color)
elif item.text().startswith("*"):
color = self._parse_rgba_to_qcolor(COLORS.get("YELLOW_BACKGROUND"))
item.setData(Qt.BackgroundRole, color)
item.setData(Qt.ItemDataRole.BackgroundRole, color)
else:
item.setData(
Qt.BackgroundRole, self.profile_list.palette().base().color()
Qt.ItemDataRole.BackgroundRole,
self.profile_list.palette().base().color(),
)
weights = profiles.get(name, {}).get("voices", [])
total = 0
@@ -1406,7 +1479,7 @@ class VoiceFormulaDialog(QDialog):
total += entry[1]
if total == 0:
color = self._parse_rgba_to_qcolor(COLORS.get("RED_BACKGROUND"))
item.setData(Qt.BackgroundRole, color)
item.setData(Qt.ItemDataRole.BackgroundRole, color)
self.update_profile_save_buttons()
def preview_current_mix(self):
BIN
View File
Binary file not shown.

Before

Width:  |  Height:  |  Size: 62 KiB

After

Width:  |  Height:  |  Size: 63 KiB

BIN
View File
Binary file not shown.

Before

Width:  |  Height:  |  Size: 150 KiB

After

Width:  |  Height:  |  Size: 148 KiB

+1 -1
View File
@@ -13,7 +13,7 @@ license = "MIT"
requires-python = ">=3.10, <3.13"
keywords = ["audiobook", "epub", "pdf", "text-to-speech", "subtitle", "tts", "kokoro", "accessibility", "book-converter", "voice-synthesis", "multilingual", "chapter-management", "subtitles", "content-creation", "media-generation"]
dependencies = [
"PyQt5>=5.15.11",
"PyQt6>=6.10.0",
"kokoro>=0.9.4",
"misaki[zh]>=0.9.4",
"ebooklib>=0.19",