1 Commits
Author SHA1 Message Date
Deniz Şafak 7a8df9b34e v1.1.1 2025-07-11 11:51:41 +03:00
14 changed files with 881 additions and 406 deletions
+4
View File
@@ -1,3 +1,7 @@
# v1.1.1
- Fixed adding wrong file in queue for EPUB and PDF files, ensuring the correct file is added to the queue.
- Reformatted the code using Black.
# v1.1.0 # v1.1.0
- Added queue system for processing multiple items, allowing users to add multiple files and process them in a queue, mentioned by @jborza in #30 (Special thanks to @jborza for implementing this feature in PR #35) - Added queue system for processing multiple items, allowing users to add multiple files and process them in a queue, mentioned by @jborza in #30 (Special thanks to @jborza for implementing this feature in PR #35)
- Added a feature that allows selecting multiple items in book handler (in right click menu) by @jborza in #31, that fixes #28 - Added a feature that allows selecting multiple items in book handler (in right click menu) by @jborza in #31, that fixes #28
+1 -1
View File
@@ -1 +1 @@
1.1.0 1.1.1
+82 -38
View File
@@ -849,7 +849,7 @@ class HandlerDialog(QDialog):
if iterator.value(): if iterator.value():
has_parents = True has_parents = True
self.treeWidget.setRootIsDecorated(has_parents) self.treeWidget.setRootIsDecorated(has_parents)
def _update_checkbox_states(self): def _update_checkbox_states(self):
"""Update the checkbox states based on the current checked chapters.""" """Update the checkbox states based on the current checked chapters."""
for i in range(self.treeWidget.topLevelItemCount()): for i in range(self.treeWidget.topLevelItemCount()):
@@ -997,10 +997,21 @@ class HandlerDialog(QDialog):
bookmark_item.setData(0, Qt.UserRole, page_id) bookmark_item.setData(0, Qt.UserRole, page_id)
# only allow checking if this chapter has content # only allow checking if this chapter has content
if self.content_lengths.get(page_id, 0) > 0: if self.content_lengths.get(page_id, 0) > 0:
bookmark_item.setFlags(bookmark_item.flags() | Qt.ItemIsUserCheckable) bookmark_item.setFlags(
bookmark_item.setCheckState(0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked) bookmark_item.flags() | Qt.ItemIsUserCheckable
)
bookmark_item.setCheckState(
0,
(
Qt.Checked
if page_id in self.checked_chapters
else Qt.Unchecked
),
)
else: else:
bookmark_item.setFlags(bookmark_item.flags() & ~Qt.ItemIsUserCheckable) bookmark_item.setFlags(
bookmark_item.flags() & ~Qt.ItemIsUserCheckable
)
# map for uncategorized pages # map for uncategorized pages
self.bookmark_items_map[page_num] = bookmark_item self.bookmark_items_map[page_num] = bookmark_item
@@ -1027,10 +1038,21 @@ class HandlerDialog(QDialog):
page_item.setData(0, Qt.UserRole, page_id) page_item.setData(0, Qt.UserRole, page_id)
# only allow checking if this sub-page has content # only allow checking if this sub-page has content
if self.content_lengths.get(page_id, 0) > 0: if self.content_lengths.get(page_id, 0) > 0:
page_item.setFlags(page_item.flags() | Qt.ItemIsUserCheckable) page_item.setFlags(
page_item.setCheckState(0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked) page_item.flags() | Qt.ItemIsUserCheckable
)
page_item.setCheckState(
0,
(
Qt.Checked
if page_id in self.checked_chapters
else Qt.Unchecked
),
)
else: else:
page_item.setFlags(page_item.flags() & ~Qt.ItemIsUserCheckable) page_item.setFlags(
page_item.flags() & ~Qt.ItemIsUserCheckable
)
added_pages.add(sub_page_num) added_pages.add(sub_page_num)
@@ -1038,11 +1060,15 @@ class HandlerDialog(QDialog):
covered_pages = set(added_pages) covered_pages = set(added_pages)
# attach any pages without direct bookmarks under nearest preceding chapter # attach any pages without direct bookmarks under nearest preceding chapter
uncategorized_pages = [i for i in range(len(self.pdf_doc)) if i not in covered_pages] uncategorized_pages = [
i for i in range(len(self.pdf_doc)) if i not in covered_pages
]
for page_num in uncategorized_pages: for page_num in uncategorized_pages:
# find nearest previous bookmark # find nearest previous bookmark
prev_nums = [n for n in sorted(self.bookmark_items_map) if n < page_num] prev_nums = [n for n in sorted(self.bookmark_items_map) if n < page_num]
parent_item = self.bookmark_items_map[prev_nums[-1]] if prev_nums else self.treeWidget parent_item = (
self.bookmark_items_map[prev_nums[-1]] if prev_nums else self.treeWidget
)
page_id = f"page_{page_num+1}" page_id = f"page_{page_num+1}"
title = f"Page {page_num+1}" title = f"Page {page_num+1}"
text = self.content_texts.get(page_id, "").strip() text = self.content_texts.get(page_id, "").strip()
@@ -1055,7 +1081,9 @@ class HandlerDialog(QDialog):
# only allow checking if uncategorized page has content # only allow checking if uncategorized page has content
if self.content_lengths.get(page_id, 0) > 0: if self.content_lengths.get(page_id, 0) > 0:
page_item.setFlags(page_item.flags() | Qt.ItemIsUserCheckable) page_item.setFlags(page_item.flags() | Qt.ItemIsUserCheckable)
page_item.setCheckState(0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked) page_item.setCheckState(
0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked
)
else: else:
page_item.setFlags(page_item.flags() & ~Qt.ItemIsUserCheckable) page_item.setFlags(page_item.flags() & ~Qt.ItemIsUserCheckable)
@@ -1081,7 +1109,9 @@ class HandlerDialog(QDialog):
# only allow checking if standalone page has content # only allow checking if standalone page has content
if self.content_lengths.get(page_id, 0) > 0: if self.content_lengths.get(page_id, 0) > 0:
page_item.setFlags(page_item.flags() | Qt.ItemIsUserCheckable) page_item.setFlags(page_item.flags() | Qt.ItemIsUserCheckable)
page_item.setCheckState(0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked) page_item.setCheckState(
0, Qt.Checked if page_id in self.checked_chapters else Qt.Unchecked
)
else: else:
page_item.setFlags(page_item.flags() & ~Qt.ItemIsUserCheckable) page_item.setFlags(page_item.flags() & ~Qt.ItemIsUserCheckable)
@@ -1182,7 +1212,7 @@ class HandlerDialog(QDialog):
self.save_chapters_checkbox = QCheckBox(checkbox_text, self) self.save_chapters_checkbox = QCheckBox(checkbox_text, self)
self.save_chapters_checkbox.setChecked(self.save_chapters_separately) self.save_chapters_checkbox.setChecked(self.save_chapters_separately)
self.save_chapters_checkbox.stateChanged.connect(self.on_save_chapters_changed) self.save_chapters_checkbox.stateChanged.connect(self.on_save_chapters_changed)
leftLayout.addWidget(self.save_chapters_checkbox) leftLayout.addWidget(self.save_chapters_checkbox)
self.merge_chapters_checkbox = QCheckBox( self.merge_chapters_checkbox = QCheckBox(
"Create a merged version at the end", self "Create a merged version at the end", self
) )
@@ -1191,7 +1221,7 @@ class HandlerDialog(QDialog):
self.on_merge_chapters_changed self.on_merge_chapters_changed
) )
leftLayout.addWidget(self.merge_chapters_checkbox) leftLayout.addWidget(self.merge_chapters_checkbox)
self.save_as_project_checkbox = QCheckBox( self.save_as_project_checkbox = QCheckBox(
"Save in a project folder with metadata", self "Save in a project folder with metadata", self
) )
@@ -1501,7 +1531,9 @@ class HandlerDialog(QDialog):
authors_text = ", ".join(self.book_metadata["authors"]) authors_text = ", ".join(self.book_metadata["authors"])
html_content += f"<p style='text-align: center; font-style: italic;'>By {authors_text}</p>" html_content += f"<p style='text-align: center; font-style: italic;'>By {authors_text}</p>"
if self.book_metadata["publisher"] or self.book_metadata.get("publication_year"): if self.book_metadata["publisher"] or self.book_metadata.get(
"publication_year"
):
pub_info = [] pub_info = []
if self.book_metadata["publisher"]: if self.book_metadata["publisher"]:
pub_info.append(f"Published by {self.book_metadata['publisher']}") pub_info.append(f"Published by {self.book_metadata['publisher']}")
@@ -1543,7 +1575,9 @@ class HandlerDialog(QDialog):
try: try:
author_items = self.book.get_metadata("DC", "creator") author_items = self.book.get_metadata("DC", "creator")
if author_items: if author_items:
metadata["authors"] = [author[0] for author in author_items if len(author) > 0] metadata["authors"] = [
author[0] for author in author_items if len(author) > 0
]
except Exception as e: except Exception as e:
logging.warning(f"Error extracting author metadata: {e}") logging.warning(f"Error extracting author metadata: {e}")
@@ -1560,14 +1594,14 @@ class HandlerDialog(QDialog):
metadata["publisher"] = publisher_items[0][0] metadata["publisher"] = publisher_items[0][0]
except Exception as e: except Exception as e:
logging.warning(f"Error extracting publisher metadata: {e}") logging.warning(f"Error extracting publisher metadata: {e}")
# Try to extract publication year # Try to extract publication year
try: try:
date_items = self.book.get_metadata("DC", "date") date_items = self.book.get_metadata("DC", "date")
if date_items and len(date_items) > 0: if date_items and len(date_items) > 0:
date_str = date_items[0][0] date_str = date_items[0][0]
# Try to extract just the year from the date string # Try to extract just the year from the date string
year_match = re.search(r'\b(19|20)\d{2}\b', date_str) year_match = re.search(r"\b(19|20)\d{2}\b", date_str)
if year_match: if year_match:
metadata["publication_year"] = year_match.group(0) metadata["publication_year"] = year_match.group(0)
else: else:
@@ -1603,16 +1637,16 @@ class HandlerDialog(QDialog):
metadata["description"] = f"Keywords: {keywords}" metadata["description"] = f"Keywords: {keywords}"
metadata["publisher"] = pdf_info.get("creator", None) metadata["publisher"] = pdf_info.get("creator", None)
# Try to extract publication date from PDF metadata # Try to extract publication date from PDF metadata
if "creationDate" in pdf_info: if "creationDate" in pdf_info:
date_str = pdf_info["creationDate"] date_str = pdf_info["creationDate"]
year_match = re.search(r'D:(\d{4})', date_str) year_match = re.search(r"D:(\d{4})", date_str)
if year_match: if year_match:
metadata["publication_year"] = year_match.group(1) metadata["publication_year"] = year_match.group(1)
elif "modDate" in pdf_info: elif "modDate" in pdf_info:
date_str = pdf_info["modDate"] date_str = pdf_info["modDate"]
year_match = re.search(r'D:(\d{4})', date_str) year_match = re.search(r"D:(\d{4})", date_str)
if year_match: if year_match:
metadata["publication_year"] = year_match.group(1) metadata["publication_year"] = year_match.group(1)
@@ -1634,22 +1668,26 @@ class HandlerDialog(QDialog):
def _format_metadata_tags(self): def _format_metadata_tags(self):
"""Format metadata tags for insertion at the beginning of the text""" """Format metadata tags for insertion at the beginning of the text"""
import datetime import datetime
metadata = self.book_metadata metadata = self.book_metadata
filename = os.path.splitext(os.path.basename(self.book_path))[0] filename = os.path.splitext(os.path.basename(self.book_path))[0]
current_year = str(datetime.datetime.now().year) current_year = str(datetime.datetime.now().year)
# Get values with fallbacks # Get values with fallbacks
title = metadata.get("title") or filename title = metadata.get("title") or filename
authors = metadata.get("authors") or ["Unknown"] authors = metadata.get("authors") or ["Unknown"]
authors_text = ", ".join(authors) authors_text = ", ".join(authors)
album_artist = authors_text or "Unknown" album_artist = authors_text or "Unknown"
year = metadata.get("publication_year") or current_year # Use publication year if available year = (
metadata.get("publication_year") or current_year
) # Use publication year if available
# Count chapters/pages # Count chapters/pages
total_chapters = len(self.checked_chapters) total_chapters = len(self.checked_chapters)
chapter_text = f"{total_chapters} {'Chapters' if self.file_type == 'epub' else 'Pages'}" chapter_text = (
f"{total_chapters} {'Chapters' if self.file_type == 'epub' else 'Pages'}"
)
# Format metadata tags # Format metadata tags
metadata_tags = [ metadata_tags = [
f"<<METADATA_TITLE:{title}>>", f"<<METADATA_TITLE:{title}>>",
@@ -1658,9 +1696,9 @@ class HandlerDialog(QDialog):
f"<<METADATA_YEAR:{year}>>", f"<<METADATA_YEAR:{year}>>",
f"<<METADATA_ALBUM_ARTIST:{album_artist}>>", f"<<METADATA_ALBUM_ARTIST:{album_artist}>>",
f"<<METADATA_COMPOSER:Narrator>>", f"<<METADATA_COMPOSER:Narrator>>",
f"<<METADATA_GENRE:Audiobook>>" f"<<METADATA_GENRE:Audiobook>>",
] ]
return "\n".join(metadata_tags) return "\n".join(metadata_tags)
def _get_epub_selected_text(self): def _get_epub_selected_text(self):
@@ -1669,7 +1707,7 @@ class HandlerDialog(QDialog):
# Add metadata tags at the beginning # Add metadata tags at the beginning
metadata_tags = self._format_metadata_tags() metadata_tags = self._format_metadata_tags()
item_order_counter = 0 item_order_counter = 0
ordered_checked_items = [] ordered_checked_items = []
@@ -1730,7 +1768,10 @@ class HandlerDialog(QDialog):
if text: if text:
all_content.append(text) all_content.append(text)
included_text_ids.add(page_id) included_text_ids.add(page_id)
return metadata_tags + "\n\n" + "\n\n".join(all_content), all_checked_identifiers return (
metadata_tags + "\n\n" + "\n\n".join(all_content),
all_checked_identifiers,
)
iterator = QTreeWidgetItemIterator(self.treeWidget) iterator = QTreeWidgetItemIterator(self.treeWidget)
while iterator.value(): while iterator.value():
@@ -1788,7 +1829,10 @@ class HandlerDialog(QDialog):
included_text_ids.add(identifier) included_text_ids.add(identifier)
iterator += 1 iterator += 1
return metadata_tags + "\n\n" + "\n\n".join([t[1] for t in section_titles]), all_checked_identifiers return (
metadata_tags + "\n\n" + "\n\n".join([t[1] for t in section_titles]),
all_checked_identifiers,
)
def on_save_chapters_changed(self, state): def on_save_chapters_changed(self, state):
self.save_chapters_separately = bool(state) self.save_chapters_separately = bool(state)
@@ -1815,21 +1859,21 @@ class HandlerDialog(QDialog):
def get_save_as_project(self): def get_save_as_project(self):
return self.save_as_project return self.save_as_project
def check_selected_items(self): def check_selected_items(self):
self.set_selected_items_checked(True) self.set_selected_items_checked(True)
def uncheck_selected_items(self): def uncheck_selected_items(self):
self.set_selected_items_checked(False) self.set_selected_items_checked(False)
def set_selected_items_checked(self, state: bool): def set_selected_items_checked(self, state: bool):
print(f"Checking selected items: {state}") print(f"Checking selected items: {state}")
self.treeWidget.blockSignals(True) self.treeWidget.blockSignals(True)
for item in self.treeWidget.selectedItems(): for item in self.treeWidget.selectedItems():
if item.flags() & Qt.ItemIsUserCheckable: if item.flags() & Qt.ItemIsUserCheckable:
item.setCheckState(0, Qt.Checked if state else Qt.Unchecked) item.setCheckState(0, Qt.Checked if state else Qt.Unchecked)
self.treeWidget.blockSignals(False) self.treeWidget.blockSignals(False)
self._update_checked_set_from_tree() self._update_checked_set_from_tree()
def on_tree_context_menu(self, pos): def on_tree_context_menu(self, pos):
item = self.treeWidget.itemAt(pos) item = self.treeWidget.itemAt(pos)
@@ -1842,7 +1886,7 @@ class HandlerDialog(QDialog):
action.triggered.connect(self.uncheck_selected_items) action.triggered.connect(self.uncheck_selected_items)
menu.exec_(self.treeWidget.mapToGlobal(pos)) menu.exec_(self.treeWidget.mapToGlobal(pos))
return return
if ( if (
not item not item
or item.childCount() == 0 or item.childCount() == 0
+1 -1
View File
@@ -129,4 +129,4 @@ COLORS = {
"DARK_DISABLED": "#535353", "DARK_DISABLED": "#535353",
"LIGHT_BG": "#eff0f1", "LIGHT_BG": "#eff0f1",
"LIGHT_DISABLED": "#9a9999", "LIGHT_DISABLED": "#9a9999",
} }
+281 -141
View File
@@ -10,13 +10,20 @@ from PyQt5.QtCore import QThread, pyqtSignal, Qt, QTimer
from PyQt5.QtWidgets import QCheckBox, QVBoxLayout, QDialog, QLabel, QDialogButtonBox from PyQt5.QtWidgets import QCheckBox, QVBoxLayout, QDialog, QLabel, QDialogButtonBox
import soundfile as sf import soundfile as sf
from abogen.utils import clean_text, create_process from abogen.utils import clean_text, create_process
from abogen.constants import PROGRAM_NAME, LANGUAGE_DESCRIPTIONS, SAMPLE_VOICE_TEXTS, COLORS, CHAPTER_OPTIONS_COUNTDOWN from abogen.constants import (
PROGRAM_NAME,
LANGUAGE_DESCRIPTIONS,
SAMPLE_VOICE_TEXTS,
COLORS,
CHAPTER_OPTIONS_COUNTDOWN,
)
from abogen.voice_formulas import get_new_voice from abogen.voice_formulas import get_new_voice
import abogen.hf_tracker as hf_tracker import abogen.hf_tracker as hf_tracker
import static_ffmpeg import static_ffmpeg
import threading # for efficient waiting import threading # for efficient waiting
import subprocess import subprocess
def get_sample_voice_text(lang_code): def get_sample_voice_text(lang_code):
return SAMPLE_VOICE_TEXTS.get(lang_code, SAMPLE_VOICE_TEXTS["a"]) return SAMPLE_VOICE_TEXTS.get(lang_code, SAMPLE_VOICE_TEXTS["a"])
@@ -73,7 +80,9 @@ class ChapterOptionsDialog(QDialog):
# Countdown label # Countdown label
self.countdown_seconds = CHAPTER_OPTIONS_COUNTDOWN self.countdown_seconds = CHAPTER_OPTIONS_COUNTDOWN
self.countdown_label = QLabel(f"Auto-accepting in {self.countdown_seconds} seconds...") self.countdown_label = QLabel(
f"Auto-accepting in {self.countdown_seconds} seconds..."
)
self.countdown_label.setStyleSheet(f"color: {COLORS['GREEN']};") self.countdown_label.setStyleSheet(f"color: {COLORS['GREEN']};")
layout.addWidget(self.countdown_label) layout.addWidget(self.countdown_label)
@@ -96,7 +105,9 @@ class ChapterOptionsDialog(QDialog):
def _on_timer_tick(self): def _on_timer_tick(self):
self.countdown_seconds -= 1 self.countdown_seconds -= 1
if self.countdown_seconds > 0: if self.countdown_seconds > 0:
self.countdown_label.setText(f"Auto-accepting in {self.countdown_seconds} seconds...") self.countdown_label.setText(
f"Auto-accepting in {self.countdown_seconds} seconds..."
)
else: else:
self._timer.stop() self._timer.stop()
self._button_box.accepted.emit() # Simulate OK click self._button_box.accepted.emit() # Simulate OK click
@@ -152,7 +163,7 @@ class ConversionThread(QThread):
start_time, start_time,
total_char_count, total_char_count,
use_gpu=True, use_gpu=True,
from_queue=False from_queue=False,
): # Add use_gpu parameter ): # Add use_gpu parameter
super().__init__() super().__init__()
self._chapter_options_event = threading.Event() self._chapter_options_event = threading.Event()
@@ -182,15 +193,17 @@ class ConversionThread(QThread):
self.use_gpu = use_gpu # Store the GPU setting self.use_gpu = use_gpu # Store the GPU setting
self.max_subtitle_words = 50 # Default value, will be overridden from GUI self.max_subtitle_words = 50 # Default value, will be overridden from GUI
def _stream_audio_in_chunks(self, segments, process_func, progress_prefix="Processing"): def _stream_audio_in_chunks(
self, segments, process_func, progress_prefix="Processing"
):
""" """
Process audio segments in memory-efficient chunks Process audio segments in memory-efficient chunks
Args: Args:
segments: List of audio segments to process segments: List of audio segments to process
process_func: Function that takes (segment_bytes, is_last) and processes a chunk process_func: Function that takes (segment_bytes, is_last) and processes a chunk
progress_prefix: Prefix for progress messages progress_prefix: Prefix for progress messages
Returns: Returns:
Total samples processed Total samples processed
""" """
@@ -199,83 +212,98 @@ class ConversionThread(QThread):
samples_processed = 0 samples_processed = 0
self.log_updated.emit(f"\n{progress_prefix} segments...") self.log_updated.emit(f"\n{progress_prefix} segments...")
# Stream each segment individually # Stream each segment individually
for i, segment in enumerate(segments): for i, segment in enumerate(segments):
try: try:
# Handle both NumPy arrays and PyTorch tensors # Handle both NumPy arrays and PyTorch tensors
if hasattr(segment, 'astype'): if hasattr(segment, "astype"):
segment_bytes = segment.astype("float32").tobytes() segment_bytes = segment.astype("float32").tobytes()
else: else:
segment_bytes = segment.cpu().numpy().astype("float32").tobytes() segment_bytes = segment.cpu().numpy().astype("float32").tobytes()
is_last = (i == len(segments) - 1) is_last = i == len(segments) - 1
# Update progress periodically - skip if there's only one segment # Update progress periodically - skip if there's only one segment
if (i % 20 == 0 or is_last) and len(segments) > 1: if (i % 20 == 0 or is_last) and len(segments) > 1:
progress_percent = int((samples_processed / total_samples) * 100) progress_percent = int((samples_processed / total_samples) * 100)
self.log_updated.emit(f"{progress_prefix} segment {i+1}/{len(segments)} ({progress_percent}% complete)") self.log_updated.emit(
f"{progress_prefix} segment {i+1}/{len(segments)} ({progress_percent}% complete)"
)
# Process this segment # Process this segment
process_func(segment_bytes, is_last) process_func(segment_bytes, is_last)
# Update samples processed # Update samples processed
samples_processed += len(segment) samples_processed += len(segment)
# Clear segment bytes from memory # Clear segment bytes from memory
del segment_bytes del segment_bytes
except Exception as e: except Exception as e:
self.log_updated.emit(f"Error processing segment {i}: {str(e)}") self.log_updated.emit(f"Error processing segment {i}: {str(e)}")
raise raise
return samples_processed return samples_processed
def _process_audio_segments(self, audio_segments, output_path, output_format, use_ffmpeg=False, ffmpeg_args=None): def _process_audio_segments(
self,
audio_segments,
output_path,
output_format,
use_ffmpeg=False,
ffmpeg_args=None,
):
""" """
Process audio segments to a target format with memory-efficient handling Process audio segments to a target format with memory-efficient handling
Args: Args:
audio_segments: List of audio segments to process audio_segments: List of audio segments to process
output_path: Path for output file output_path: Path for output file
output_format: Format of output (wav, mp3, flac, opus, m4b) output_format: Format of output (wav, mp3, flac, opus, m4b)
use_ffmpeg: Whether to use FFmpeg instead of soundfile use_ffmpeg: Whether to use FFmpeg instead of soundfile
ffmpeg_args: Optional additional FFmpeg arguments when use_ffmpeg=True ffmpeg_args: Optional additional FFmpeg arguments when use_ffmpeg=True
Returns: Returns:
Tuple of (success, output_path) Tuple of (success, output_path)
""" """
self.log_updated.emit(f"\nProcessing audio data to {output_format.upper()}...") self.log_updated.emit(f"\nProcessing audio data to {output_format.upper()}...")
segments_count = len(audio_segments) segments_count = len(audio_segments)
# Handle direct streaming for WAV (the only format supporting append mode) # Handle direct streaming for WAV (the only format supporting append mode)
if output_format == "wav" and not use_ffmpeg: if output_format == "wav" and not use_ffmpeg:
try: try:
# Write first segment # Write first segment
sf.write(output_path, audio_segments[0], 24000, format="wav") sf.write(output_path, audio_segments[0], 24000, format="wav")
# Append remaining segments # Append remaining segments
for i, segment in enumerate(audio_segments[1:], 1): for i, segment in enumerate(audio_segments[1:], 1):
with sf.SoundFile(output_path, mode='r+') as f: with sf.SoundFile(output_path, mode="r+") as f:
f.seek(0, sf.SEEK_END) f.seek(0, sf.SEEK_END)
f.write(segment) f.write(segment)
return True, output_path return True, output_path
except Exception as e: except Exception as e:
self.log_updated.emit((f"Error writing WAV file: {str(e)}", "red")) self.log_updated.emit((f"Error writing WAV file: {str(e)}", "red"))
return False, None return False, None
# For formats requiring FFmpeg (opus, m4b) or when explicitly requested # For formats requiring FFmpeg (opus, m4b) or when explicitly requested
if use_ffmpeg or output_format in ["opus", "m4b"]: if use_ffmpeg or output_format in ["opus", "m4b"]:
static_ffmpeg.add_paths() static_ffmpeg.add_paths()
# Basic FFmpeg command # Basic FFmpeg command
cmd = [ cmd = [
"ffmpeg", "-y", "ffmpeg",
"-thread_queue_size", "32768", "-y",
"-f", "f32le", "-thread_queue_size",
"-ar", "24000", "32768",
"-ac", "1", "-f",
"-i", "pipe:0" "f32le",
"-ar",
"24000",
"-ac",
"1",
"-i",
"pipe:0",
] ]
# Add custom FFmpeg arguments if provided # Add custom FFmpeg arguments if provided
if ffmpeg_args: if ffmpeg_args:
cmd.extend(ffmpeg_args) cmd.extend(ffmpeg_args)
@@ -289,48 +317,62 @@ class ConversionThread(QThread):
cmd.extend(["-c:a", "flac", "-compression_level", "8"]) cmd.extend(["-c:a", "flac", "-compression_level", "8"])
else: else:
cmd.extend(["-c:a", "aac", "-q:a", "2"]) cmd.extend(["-c:a", "aac", "-q:a", "2"])
# Add output path # Add output path
cmd.append(output_path) cmd.append(output_path)
# Create process # Create process
proc = create_process(cmd, stdin=subprocess.PIPE, text=False) proc = create_process(cmd, stdin=subprocess.PIPE, text=False)
# Process segments # Process segments
try: try:
# Use the unified streaming function # Use the unified streaming function
def process_chunk(chunk_bytes, is_last): def process_chunk(chunk_bytes, is_last):
proc.stdin.write(chunk_bytes) proc.stdin.write(chunk_bytes)
self._stream_audio_in_chunks(audio_segments, process_chunk, self._stream_audio_in_chunks(
progress_prefix=f"Processing {output_format.upper()}") audio_segments,
process_chunk,
progress_prefix=f"Processing {output_format.upper()}",
)
# Close stdin and wait for process to complete # Close stdin and wait for process to complete
proc.stdin.close() proc.stdin.close()
if proc.wait() != 0: if proc.wait() != 0:
self.log_updated.emit((f"{output_format.upper()} conversion failed.", "red")) self.log_updated.emit(
(f"{output_format.upper()} conversion failed.", "red")
)
return False, None return False, None
return True, output_path return True, output_path
except Exception as e: except Exception as e:
self.log_updated.emit((f"Error during {output_format.upper()} conversion: {str(e)}", "red")) self.log_updated.emit(
(
f"Error during {output_format.upper()} conversion: {str(e)}",
"red",
)
)
proc.stdin.close() proc.stdin.close()
try: try:
proc.terminate() proc.terminate()
except: except:
pass pass
return False, None return False, None
# For formats supported by soundfile (mp3, flac) # For formats supported by soundfile (mp3, flac)
else: else:
try: try:
with sf.SoundFile(output_path, 'w', samplerate=24000, channels=1, format=output_format) as f: with sf.SoundFile(
output_path, "w", samplerate=24000, channels=1, format=output_format
) as f:
for i, segment in enumerate(audio_segments): for i, segment in enumerate(audio_segments):
f.write(segment) f.write(segment)
return True, output_path return True, output_path
except Exception as e: except Exception as e:
self.log_updated.emit((f"Error processing {output_format.upper()} file: {str(e)}", "red")) self.log_updated.emit(
(f"Error processing {output_format.upper()} file: {str(e)}", "red")
)
return False, None return False, None
def run(self): def run(self):
@@ -341,12 +383,14 @@ class ConversionThread(QThread):
hf_tracker.set_log_callback(lambda msg: self.log_updated.emit(msg)) hf_tracker.set_log_callback(lambda msg: self.log_updated.emit(msg))
# Show configuration # Show configuration
self.log_updated.emit("Configuration:") self.log_updated.emit("Configuration:")
# Use file_name for logs if from_queue, otherwise use display_path if available # Use file_name for logs if from_queue, otherwise use display_path if available
if getattr(self, "from_queue", False): if getattr(self, "from_queue", False):
display_file = self.file_name display_file = self.file_name
else: else:
display_file = self.display_path if self.display_path else self.file_name display_file = (
self.display_path if self.display_path else self.file_name
)
self.log_updated.emit(f"- Input File: {display_file}") self.log_updated.emit(f"- Input File: {display_file}")
@@ -363,7 +407,9 @@ class ConversionThread(QThread):
self.log_updated.emit(f"- Speed: {self.speed}") self.log_updated.emit(f"- Speed: {self.speed}")
self.log_updated.emit(f"- Subtitle mode: {self.subtitle_mode}") self.log_updated.emit(f"- Subtitle mode: {self.subtitle_mode}")
self.log_updated.emit(f"- Output format: {self.output_format}") self.log_updated.emit(f"- Output format: {self.output_format}")
self.log_updated.emit(f"- Subtitle format: {getattr(self, 'subtitle_format', 'srt')}") self.log_updated.emit(
f"- Subtitle format: {getattr(self, 'subtitle_format', 'srt')}"
)
self.log_updated.emit(f"- Save option: {self.save_option}") self.log_updated.emit(f"- Save option: {self.save_option}")
if self.replace_single_newlines: if self.replace_single_newlines:
self.log_updated.emit(f"- Replace single newlines: Yes") self.log_updated.emit(f"- Replace single newlines: Yes")
@@ -382,8 +428,10 @@ class ConversionThread(QThread):
f"- Merge chapters at the end: {'Yes' if merge_at_end else 'No'}" f"- Merge chapters at the end: {'Yes' if merge_at_end else 'No'}"
) )
# Display the separate chapters format if it's set # Display the separate chapters format if it's set
separate_format = getattr(self, 'separate_chapters_format', 'wav') separate_format = getattr(self, "separate_chapters_format", "wav")
self.log_updated.emit(f"- Separate chapters format: {separate_format}") self.log_updated.emit(
f"- Separate chapters format: {separate_format}"
)
if self.save_option == "Choose output folder": if self.save_option == "Choose output folder":
self.log_updated.emit( self.log_updated.emit(
@@ -408,7 +456,7 @@ class ConversionThread(QThread):
# Clean up text using utility function # Clean up text using utility function
text = clean_text(text) text = clean_text(text)
# Remove metadata markers from the text to be processed # Remove metadata markers from the text to be processed
metadata_pattern = r"<<METADATA_[^:]+:[^>]*>>" metadata_pattern = r"<<METADATA_[^:]+:[^>]*>>"
text = re.sub(metadata_pattern, "", text) text = re.sub(metadata_pattern, "", text)
@@ -478,7 +526,6 @@ class ConversionThread(QThread):
chapters_out_dir = None chapters_out_dir = None
suffix = "" suffix = ""
# Use file_name for logs if from_queue, otherwise use display_path if available # Use file_name for logs if from_queue, otherwise use display_path if available
if getattr(self, "from_queue", False): if getattr(self, "from_queue", False):
base_path = self.file_name base_path = self.file_name
@@ -701,42 +748,61 @@ class ConversionThread(QThread):
# Find last word boundary before limit # Find last word boundary before limit
pos = sanitized[:MAX_LEN].rfind("_") pos = sanitized[:MAX_LEN].rfind("_")
# Use word boundary if found, otherwise use hard limit # Use word boundary if found, otherwise use hard limit
sanitized = sanitized[:pos if pos > 0 else MAX_LEN].rstrip("_") sanitized = sanitized[: pos if pos > 0 else MAX_LEN].rstrip("_")
chapter_filename = f"{chapter_idx:02d}_{sanitized}" chapter_filename = f"{chapter_idx:02d}_{sanitized}"
# Use separate_chapters_format # Use separate_chapters_format
separate_format = getattr(self, 'separate_chapters_format', 'wav') separate_format = getattr(self, "separate_chapters_format", "wav")
chapter_out_path = os.path.join( chapter_out_path = os.path.join(
chapters_out_dir, f"{chapter_filename}.{separate_format}" chapters_out_dir, f"{chapter_filename}.{separate_format}"
) )
# Process audio segments using the unified function # Process audio segments using the unified function
success, chapter_out_path = self._process_audio_segments( success, chapter_out_path = self._process_audio_segments(
chapter_audio_segments, chapter_out_path, separate_format, use_ffmpeg=(separate_format in ["opus", "m4b"]) chapter_audio_segments,
chapter_out_path,
separate_format,
use_ffmpeg=(separate_format in ["opus", "m4b"]),
) )
if not success: if not success:
self.log_updated.emit((f"Failed to write {separate_format.upper()} file.", "red")) self.log_updated.emit(
(f"Failed to write {separate_format.upper()} file.", "red")
)
continue continue
# Generate subtitle file for chapter if not Disabled # Generate subtitle file for chapter if not Disabled
if self.subtitle_mode != "Disabled" and chapter_subtitle_entries: if self.subtitle_mode != "Disabled" and chapter_subtitle_entries:
subtitle_format = getattr(self, 'subtitle_format', 'srt') subtitle_format = getattr(self, "subtitle_format", "srt")
file_extension = 'ass' if 'ass' in subtitle_format else 'srt' file_extension = "ass" if "ass" in subtitle_format else "srt"
chapter_subtitle_path = os.path.join( chapter_subtitle_path = os.path.join(
chapters_out_dir, f"{chapter_filename}.{file_extension}" chapters_out_dir, f"{chapter_filename}.{file_extension}"
) )
if 'ass' in subtitle_format: if "ass" in subtitle_format:
# Generate ASS subtitle # Generate ASS subtitle
is_centered = subtitle_format in ("ass_centered_wide", "ass_centered_narrow") is_centered = subtitle_format in (
is_narrow = subtitle_format in ("ass_narrow", "ass_centered_narrow") "ass_centered_wide",
self._write_ass_subtitle(chapter_subtitle_path, chapter_subtitle_entries, is_centered, is_narrow) "ass_centered_narrow",
)
is_narrow = subtitle_format in (
"ass_narrow",
"ass_centered_narrow",
)
self._write_ass_subtitle(
chapter_subtitle_path,
chapter_subtitle_entries,
is_centered,
is_narrow,
)
else: else:
# Generate SRT subtitle (default) # Generate SRT subtitle (default)
with open( with open(
chapter_subtitle_path, "w", encoding="utf-8", errors="replace" chapter_subtitle_path,
"w",
encoding="utf-8",
errors="replace",
) as srt_file: ) as srt_file:
for i, (start, end, text) in enumerate( for i, (start, end, text) in enumerate(
chapter_subtitle_entries, 1 chapter_subtitle_entries, 1
@@ -768,8 +834,8 @@ class ConversionThread(QThread):
or not self.save_chapters_separately or not self.save_chapters_separately
or getattr(self, "merge_chapters_at_end", True) or getattr(self, "merge_chapters_at_end", True)
) )
intended_output_format = self.output_format # Store the original choice intended_output_format = self.output_format # Store the original choice
if audio_segments and merge_chapters: if audio_segments and merge_chapters:
self.log_updated.emit("\nFinalizing audio file...") self.log_updated.emit("\nFinalizing audio file...")
@@ -778,7 +844,7 @@ class ConversionThread(QThread):
base_filepath_no_ext = os.path.join(out_dir, f"{base_name}{suffix}") base_filepath_no_ext = os.path.join(out_dir, f"{base_name}{suffix}")
final_out_path = None final_out_path = None
# Use dedicated chapter processing for M4B when we have chapters # Use dedicated chapter processing for M4B when we have chapters
if intended_output_format == "m4b": if intended_output_format == "m4b":
self.log_updated.emit("\nGenerating audio with chapters...") self.log_updated.emit("\nGenerating audio with chapters...")
@@ -788,35 +854,52 @@ class ConversionThread(QThread):
else: else:
# Process audio segments using the unified function # Process audio segments using the unified function
success, final_out_path = self._process_audio_segments( success, final_out_path = self._process_audio_segments(
audio_segments, f"{base_filepath_no_ext}.{intended_output_format}", audio_segments,
intended_output_format, f"{base_filepath_no_ext}.{intended_output_format}",
use_ffmpeg=(intended_output_format in ["opus", "m4b"]) intended_output_format,
use_ffmpeg=(intended_output_format in ["opus", "m4b"]),
) )
if not success: if not success:
final_out_path = None final_out_path = None
if not final_out_path: if not final_out_path:
self.log_updated.emit(("Audio generation failed.", "red")) self.log_updated.emit(("Audio generation failed.", "red"))
self.conversion_finished.emit(("Audio generation failed.", "red"), None) self.conversion_finished.emit(
("Audio generation failed.", "red"), None
)
return return
# Subtitle and final message logic # Subtitle and final message logic
if final_out_path: if final_out_path:
if self.subtitle_mode != "Disabled": if self.subtitle_mode != "Disabled":
subtitle_format = getattr(self, 'subtitle_format', 'srt') subtitle_format = getattr(self, "subtitle_format", "srt")
file_extension = 'ass' if 'ass' in subtitle_format else 'srt' file_extension = "ass" if "ass" in subtitle_format else "srt"
subtitle_path = os.path.splitext(final_out_path)[0] + f".{file_extension}" subtitle_path = (
os.path.splitext(final_out_path)[0] + f".{file_extension}"
if 'ass' in subtitle_format: )
if "ass" in subtitle_format:
# Generate ASS subtitle # Generate ASS subtitle
is_centered = subtitle_format in ("ass_centered_wide", "ass_centered_narrow") is_centered = subtitle_format in (
is_narrow = subtitle_format in ("ass_narrow", "ass_centered_narrow") "ass_centered_wide",
self._write_ass_subtitle(subtitle_path, subtitle_entries, is_centered, is_narrow) "ass_centered_narrow",
)
is_narrow = subtitle_format in (
"ass_narrow",
"ass_centered_narrow",
)
self._write_ass_subtitle(
subtitle_path, subtitle_entries, is_centered, is_narrow
)
else: else:
# Generate SRT subtitle (default) # Generate SRT subtitle (default)
with open(subtitle_path, "w", encoding="utf-8", errors="replace") as srt_file: with open(
for i, (start, end, text) in enumerate(subtitle_entries, 1): subtitle_path, "w", encoding="utf-8", errors="replace"
) as srt_file:
for i, (start, end, text) in enumerate(
subtitle_entries, 1
):
srt_file.write( srt_file.write(
f"{i}\n{self._srt_time(start)} --> {self._srt_time(end)}\n{text}\n\n" f"{i}\n{self._srt_time(start)} --> {self._srt_time(end)}\n{text}\n\n"
) )
@@ -829,11 +912,16 @@ class ConversionThread(QThread):
) )
else: else:
self.conversion_finished.emit( self.conversion_finished.emit(
(f"\nAudiobook saved to: {final_out_path}", "green"), final_out_path (f"\nAudiobook saved to: {final_out_path}", "green"),
final_out_path,
) )
else: else:
self.log_updated.emit(("Audio generation failed (final_out_path was not set).", "red")) self.log_updated.emit(
self.conversion_finished.emit(("Audio generation failed.", "red"), None) ("Audio generation failed (final_out_path was not set).", "red")
)
self.conversion_finished.emit(
("Audio generation failed.", "red"), None
)
elif audio_segments and not merge_chapters: elif audio_segments and not merge_chapters:
self.conversion_finished.emit( self.conversion_finished.emit(
( (
@@ -856,12 +944,14 @@ class ConversionThread(QThread):
self.waiting_for_user_input = False self.waiting_for_user_input = False
self._chapter_options_event.set() self._chapter_options_event.set()
def _generate_m4b_with_chapters(self, audio_segments, chapters_time, base_filepath_no_ext): def _generate_m4b_with_chapters(
self, audio_segments, chapters_time, base_filepath_no_ext
):
"""Generate M4B file with chapters from audio segments""" """Generate M4B file with chapters from audio segments"""
final_wav_path = f"{base_filepath_no_ext}.wav" final_wav_path = f"{base_filepath_no_ext}.wav"
output_m4b_path = f"{base_filepath_no_ext}.m4b" output_m4b_path = f"{base_filepath_no_ext}.m4b"
chapters_info_path = f"{base_filepath_no_ext}_chapters.txt" chapters_info_path = f"{base_filepath_no_ext}_chapters.txt"
# Early check for single/no chapter case # Early check for single/no chapter case
if not chapters_time or len(chapters_time) <= 1: if not chapters_time or len(chapters_time) <= 1:
self.log_updated.emit( self.log_updated.emit(
@@ -877,7 +967,9 @@ class ConversionThread(QThread):
if success: if success:
return wav_path return wav_path
else: else:
self.log_updated.emit((f"\nFailed to save single/no chapter audio as WAV", "red")) self.log_updated.emit(
(f"\nFailed to save single/no chapter audio as WAV", "red")
)
return None return None
try: try:
@@ -885,46 +977,61 @@ class ConversionThread(QThread):
with open(chapters_info_path, "w", encoding="utf-8") as f: with open(chapters_info_path, "w", encoding="utf-8") as f:
f.write(";FFMETADATA1\n") f.write(";FFMETADATA1\n")
for chapter in chapters_time: for chapter in chapters_time:
chapter_title = chapter['chapter'].replace('=', '\\=') chapter_title = chapter["chapter"].replace("=", "\\=")
f.write(f"[CHAPTER]\n") f.write(f"[CHAPTER]\n")
f.write(f"TIMEBASE=1/1000\n") f.write(f"TIMEBASE=1/1000\n")
f.write(f"START={int(chapter['start']*1000)}\n") f.write(f"START={int(chapter['start']*1000)}\n")
f.write(f"END={int(chapter['end']*1000)}\n") f.write(f"END={int(chapter['end']*1000)}\n")
f.write(f"title={chapter_title}\n\n") f.write(f"title={chapter_title}\n\n")
# For M4B with chapters, we need to use input file for chapter information # For M4B with chapters, we need to use input file for chapter information
static_ffmpeg.add_paths() static_ffmpeg.add_paths()
metadata_options = self._extract_and_add_metadata_tags_to_ffmpeg_cmd() metadata_options = self._extract_and_add_metadata_tags_to_ffmpeg_cmd()
# Use pipe-based approach for audio input with special args for M4B chapters # Use pipe-based approach for audio input with special args for M4B chapters
ffmpeg_args = [ ffmpeg_args = [
"-i", chapters_info_path, "-i",
"-map", "0:a", chapters_info_path,
"-map_metadata", "1", "-map",
"-map_chapters", "1", "0:a",
"-map_metadata",
"1",
"-map_chapters",
"1",
*metadata_options, *metadata_options,
"-c:a", "aac", "-c:a",
"-q:a", "2", # Quality-based VBR for better quality control "aac",
"-movflags", "+faststart+use_metadata_tags", # Added for better compatibility "-q:a",
"2", # Quality-based VBR for better quality control
"-movflags",
"+faststart+use_metadata_tags", # Added for better compatibility
] ]
# Use the established unified method with M4B-specific args # Use the established unified method with M4B-specific args
success, out_path = self._process_audio_segments( success, out_path = self._process_audio_segments(
audio_segments, output_m4b_path, "m4b", use_ffmpeg=True, ffmpeg_args=ffmpeg_args audio_segments,
output_m4b_path,
"m4b",
use_ffmpeg=True,
ffmpeg_args=ffmpeg_args,
) )
# Clean up the temporary chapter metadata file # Clean up the temporary chapter metadata file
if os.path.exists(chapters_info_path): if os.path.exists(chapters_info_path):
try: try:
os.remove(chapters_info_path) os.remove(chapters_info_path)
except Exception as e: except Exception as e:
self.log_updated.emit((f"Warning: Could not delete chapters file: {e}", "orange")) self.log_updated.emit(
(f"Warning: Could not delete chapters file: {e}", "orange")
)
if success: if success:
return out_path return out_path
# If M4B generation failed, fallback to WAV # If M4B generation failed, fallback to WAV
self.log_updated.emit((f"M4B conversion failed. Falling back to WAV.\n", "red")) self.log_updated.emit(
(f"M4B conversion failed. Falling back to WAV.\n", "red")
)
success, wav_path = self._process_audio_segments( success, wav_path = self._process_audio_segments(
audio_segments, final_wav_path, "wav", use_ffmpeg=False audio_segments, final_wav_path, "wav", use_ffmpeg=False
) )
@@ -936,30 +1043,37 @@ class ConversionThread(QThread):
except Exception as e: except Exception as e:
# General error during M4B generation - create WAV file directly as final output # General error during M4B generation - create WAV file directly as final output
self.log_updated.emit((f"Error during M4B generation: {str(e)}.\n\nFalling back to WAV.\n", "red")) self.log_updated.emit(
(
f"Error during M4B generation: {str(e)}.\n\nFalling back to WAV.\n",
"red",
)
)
# Use the established unified method to create a WAV file as fallback # Use the established unified method to create a WAV file as fallback
success, wav_path = self._process_audio_segments( success, wav_path = self._process_audio_segments(
audio_segments, final_wav_path, "wav", use_ffmpeg=False audio_segments, final_wav_path, "wav", use_ffmpeg=False
) )
# Clean up temp files # Clean up temp files
if os.path.exists(chapters_info_path): if os.path.exists(chapters_info_path):
try: try:
os.remove(chapters_info_path) os.remove(chapters_info_path)
except Exception: except Exception:
pass pass
if success: if success:
return wav_path return wav_path
else: else:
self.log_updated.emit((f"Critical error: Failed to save WAV fallback", "red")) self.log_updated.emit(
(f"Critical error: Failed to save WAV fallback", "red")
)
return None return None
def _extract_and_add_metadata_tags_to_ffmpeg_cmd(self): def _extract_and_add_metadata_tags_to_ffmpeg_cmd(self):
"""Extract metadata tags from text content and add them to ffmpeg command""" """Extract metadata tags from text content and add them to ffmpeg command"""
metadata_options = [] metadata_options = []
# Get the input text (either direct or from file) # Get the input text (either direct or from file)
text = "" text = ""
if self.is_direct_text: if self.is_direct_text:
@@ -967,64 +1081,77 @@ class ConversionThread(QThread):
else: else:
try: try:
encoding = detect_encoding(self.file_name) encoding = detect_encoding(self.file_name)
with open(self.file_name, "r", encoding=encoding, errors="replace") as file: with open(
self.file_name, "r", encoding=encoding, errors="replace"
) as file:
text = file.read() text = file.read()
except Exception as e: except Exception as e:
self.log_updated.emit(f"Warning: Could not read file for metadata extraction: {e}") self.log_updated.emit(
f"Warning: Could not read file for metadata extraction: {e}"
)
return [] return []
# Extract metadata tags using regex # Extract metadata tags using regex
title_match = re.search(r"<<METADATA_TITLE:([^>]*)>>", text) title_match = re.search(r"<<METADATA_TITLE:([^>]*)>>", text)
artist_match = re.search(r"<<METADATA_ARTIST:([^>]*)>>", text) artist_match = re.search(r"<<METADATA_ARTIST:([^>]*)>>", text)
album_match = re.search(r"<<METADATA_ALBUM:([^>]*)>>", text) album_match = re.search(r"<<METADATA_ALBUM:([^>]*)>>", text)
year_match = re.search(r"<<METADATA_YEAR:([^>]*)>>", text) year_match = re.search(r"<<METADATA_YEAR:([^>]*)>>", text)
album_artist_match = re.search(r"<<METADATA_ALBUM_ARTIST:([^>]*)>>", text) album_artist_match = re.search(r"<<METADATA_ALBUM_ARTIST:([^>]*)>>", text)
composer_match = re.search(r"<<METADATA_COMPOSER:([^>]*)>>", text) composer_match = re.search(r"<<METADATA_COMPOSER:([^>]*)>>", text)
genre_match = re.search(r"<<METADATA_GENRE:([^>]*)>>", text) genre_match = re.search(r"<<METADATA_GENRE:([^>]*)>>", text)
# Use display path or filename as fallback for title # Use display path or filename as fallback for title
# Use file_name for logs if from_queue, otherwise use display_path if available # Use file_name for logs if from_queue, otherwise use display_path if available
if getattr(self, "from_queue", False): if getattr(self, "from_queue", False):
filename = os.path.splitext(os.path.basename(self.file_name))[0] filename = os.path.splitext(os.path.basename(self.file_name))[0]
else: else:
filename = os.path.splitext(os.path.basename(self.display_path if self.display_path else self.file_name))[0] filename = os.path.splitext(
os.path.basename(
self.display_path if self.display_path else self.file_name
)
)[0]
if title_match: if title_match:
metadata_options.extend(["-metadata", f"title={title_match.group(1)}"]) metadata_options.extend(["-metadata", f"title={title_match.group(1)}"])
else: else:
metadata_options.extend(["-metadata", f"title={filename}"]) metadata_options.extend(["-metadata", f"title={filename}"])
# Add artist metadata # Add artist metadata
if artist_match: if artist_match:
metadata_options.extend(["-metadata", f"artist={artist_match.group(1)}"]) metadata_options.extend(["-metadata", f"artist={artist_match.group(1)}"])
else: else:
metadata_options.extend(["-metadata", f"artist=Unknown"]) metadata_options.extend(["-metadata", f"artist=Unknown"])
# Add album metadata # Add album metadata
if album_match: if album_match:
metadata_options.extend(["-metadata", f"album={album_match.group(1)}"]) metadata_options.extend(["-metadata", f"album={album_match.group(1)}"])
else: else:
metadata_options.extend(["-metadata", f"album={filename}"]) metadata_options.extend(["-metadata", f"album={filename}"])
# Add year metadata # Add year metadata
if year_match: if year_match:
metadata_options.extend(["-metadata", f"date={year_match.group(1)}"]) metadata_options.extend(["-metadata", f"date={year_match.group(1)}"])
else: else:
# Use current year if year is not specified # Use current year if year is not specified
import datetime import datetime
current_year = datetime.datetime.now().year current_year = datetime.datetime.now().year
metadata_options.extend(["-metadata", f"date={current_year}"]) metadata_options.extend(["-metadata", f"date={current_year}"])
# Add album artist metadata # Add album artist metadata
if album_artist_match: if album_artist_match:
metadata_options.extend(["-metadata", f"album_artist={album_artist_match.group(1)}"]) metadata_options.extend(
["-metadata", f"album_artist={album_artist_match.group(1)}"]
)
else: else:
metadata_options.extend(["-metadata", f"album_artist=Unknown"]) metadata_options.extend(["-metadata", f"album_artist=Unknown"])
# Add composer metadata # Add composer metadata
if composer_match: if composer_match:
metadata_options.extend(["-metadata", f"composer={composer_match.group(1)}"]) metadata_options.extend(
["-metadata", f"composer={composer_match.group(1)}"]
)
else: else:
metadata_options.extend(["-metadata", f"composer=Narrator"]) metadata_options.extend(["-metadata", f"composer=Narrator"])
@@ -1033,7 +1160,7 @@ class ConversionThread(QThread):
metadata_options.extend(["-metadata", f"genre={genre_match.group(1)}"]) metadata_options.extend(["-metadata", f"genre={genre_match.group(1)}"])
else: else:
metadata_options.extend(["-metadata", f"genre=Audiobook"]) metadata_options.extend(["-metadata", f"genre=Audiobook"])
# Add these to ffmpeg command # Add these to ffmpeg command
return metadata_options return metadata_options
@@ -1044,7 +1171,7 @@ class ConversionThread(QThread):
s = int(t % 60) s = int(t % 60)
ms = int((t - int(t)) * 1000) ms = int((t - int(t)) * 1000)
return f"{h:02}:{m:02}:{s:02},{ms:03}" return f"{h:02}:{m:02}:{s:02},{ms:03}"
def _ass_time(self, t): def _ass_time(self, t):
"""Helper function to format time for ASS files""" """Helper function to format time for ASS files"""
h = int(t // 3600) h = int(t // 3600)
@@ -1139,17 +1266,21 @@ class ConversionThread(QThread):
(group[0]["start"], group[-1]["end"], text.strip()) (group[0]["start"], group[-1]["end"], text.strip())
) )
def _write_ass_subtitle(self, file_path, subtitle_entries, is_centered=False, is_narrow=False): def _write_ass_subtitle(
self, file_path, subtitle_entries, is_centered=False, is_narrow=False
):
with open(file_path, "w", encoding="utf-8", errors="replace") as f: with open(file_path, "w", encoding="utf-8", errors="replace") as f:
# Minimal ASS header # Minimal ASS header
f.write("[Script Info]\n") f.write("[Script Info]\n")
f.write("Title: Generated by Abogen\n") f.write("Title: Generated by Abogen\n")
f.write("ScriptType: v4.00+\n\n") f.write("ScriptType: v4.00+\n\n")
# Only events section, use override tags for positioning # Only events section, use override tags for positioning
f.write("[Events]\n") f.write("[Events]\n")
f.write("Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\n") f.write(
"Format: Layer, Start, End, Style, Name, MarginL, MarginR, MarginV, Effect, Text\n"
)
# Set margin based on is_narrow parameter # Set margin based on is_narrow parameter
margin = "90" if is_narrow else "" margin = "90" if is_narrow else ""
alignment_tag = "" alignment_tag = ""
@@ -1161,7 +1292,9 @@ class ConversionThread(QThread):
for i, (start, end, text) in enumerate(subtitle_entries, 1): for i, (start, end, text) in enumerate(subtitle_entries, 1):
start_time = self._ass_time(start) start_time = self._ass_time(start)
end_time = self._ass_time(end) end_time = self._ass_time(end)
f.write(f"Dialogue: 0,{start_time},{end_time},Default,,{margin},{margin},0,,{alignment_tag}{text}\n") f.write(
f"Dialogue: 0,{start_time},{end_time},Default,,{margin},{margin},0,,{alignment_tag}{text}\n"
)
def cancel(self): def cancel(self):
self.cancel_requested = True self.cancel_requested = True
@@ -1196,11 +1329,13 @@ class VoicePreviewThread(QThread):
self.voice = voice self.voice = voice
self.speed = speed self.speed = speed
self.use_gpu = use_gpu self.use_gpu = use_gpu
# Cache location for preview audio # Cache location for preview audio
self.cache_dir = os.path.join(tempfile.gettempdir(), PROGRAM_NAME, "preview_cache") self.cache_dir = os.path.join(
tempfile.gettempdir(), PROGRAM_NAME, "preview_cache"
)
os.makedirs(self.cache_dir, exist_ok=True) os.makedirs(self.cache_dir, exist_ok=True)
# Calculate cache path # Calculate cache path
self.cache_path = self._get_cache_path() self.cache_path = self._get_cache_path()
@@ -1208,10 +1343,12 @@ class VoicePreviewThread(QThread):
"""Generate a unique filename for the voice with its parameters""" """Generate a unique filename for the voice with its parameters"""
# For a voice formula, use a hash of the formula # For a voice formula, use a hash of the formula
if "*" in self.voice: if "*" in self.voice:
voice_id = f"voice_formula_{hashlib.md5(self.voice.encode()).hexdigest()[:8]}" voice_id = (
f"voice_formula_{hashlib.md5(self.voice.encode()).hexdigest()[:8]}"
)
else: else:
voice_id = self.voice voice_id = self.voice
# Create a unique filename based on voice_id, language, and speed # Create a unique filename based on voice_id, language, and speed
filename = f"{voice_id}_{self.lang_code}_{self.speed:.2f}.wav" filename = f"{voice_id}_{self.lang_code}_{self.speed:.2f}.wav"
return os.path.join(self.cache_dir, filename) return os.path.join(self.cache_dir, filename)
@@ -1220,7 +1357,7 @@ class VoicePreviewThread(QThread):
print( print(
f"\nVoice: {self.voice}\nLanguage: {self.lang_code}\nSpeed: {self.speed}\nGPU: {self.use_gpu}\n" f"\nVoice: {self.voice}\nLanguage: {self.lang_code}\nSpeed: {self.speed}\nGPU: {self.use_gpu}\n"
) )
# Generate the preview and save to cache # Generate the preview and save to cache
try: try:
device = "cuda" if self.use_gpu else "cpu" device = "cuda" if self.use_gpu else "cpu"
@@ -1268,7 +1405,7 @@ class PlayAudioThread(QThread):
# Wait until playback is finished or canceled # Wait until playback is finished or canceled
while pygame.mixer.music.get_busy() and not self.is_canceled: while pygame.mixer.music.get_busy() and not self.is_canceled:
_time.sleep(0.2) _time.sleep(0.2)
# Make sure to clean up regardless of how we exited the loop # Make sure to clean up regardless of how we exited the loop
try: try:
pygame.mixer.music.stop() pygame.mixer.music.stop()
@@ -1277,21 +1414,24 @@ class PlayAudioThread(QThread):
except Exception: except Exception:
# Ignore any errors during cleanup # Ignore any errors during cleanup
pass pass
self.finished.emit() self.finished.emit()
except Exception as e: except Exception as e:
# Handle initialization errors separately to give better error messages # Handle initialization errors separately to give better error messages
if "mixer not initialized" in str(e): if "mixer not initialized" in str(e):
self.error.emit("Audio playback error: The audio system was not properly initialized") self.error.emit(
"Audio playback error: The audio system was not properly initialized"
)
else: else:
self.error.emit(f"Audio playback error: {str(e)}") self.error.emit(f"Audio playback error: {str(e)}")
def stop(self): def stop(self):
"""Safely stop playback""" """Safely stop playback"""
self.is_canceled = True self.is_canceled = True
# Try to stop pygame if it's running, but catch all exceptions # Try to stop pygame if it's running, but catch all exceptions
try: try:
import pygame import pygame
if pygame.mixer.get_init(): if pygame.mixer.get_init():
if pygame.mixer.music.get_busy(): if pygame.mixer.music.get_busy():
pygame.mixer.music.stop() pygame.mixer.music.stop()
+335 -148
View File
File diff suppressed because it is too large Load Diff
+11 -2
View File
@@ -1,16 +1,20 @@
log_callback = None log_callback = None
show_warning_signal_emitter = None # Renamed for clarity show_warning_signal_emitter = None # Renamed for clarity
def set_log_callback(cb): def set_log_callback(cb):
global log_callback global log_callback
log_callback = cb log_callback = cb
def set_show_warning_signal_emitter(emitter): # Renamed for clarity def set_show_warning_signal_emitter(emitter): # Renamed for clarity
global show_warning_signal_emitter global show_warning_signal_emitter
show_warning_signal_emitter = emitter show_warning_signal_emitter = emitter
from huggingface_hub import hf_hub_download from huggingface_hub import hf_hub_download
def tracked_hf_hub_download(*args, **kwargs): def tracked_hf_hub_download(*args, **kwargs):
try: try:
local_kwargs = dict(kwargs) local_kwargs = dict(kwargs)
@@ -22,7 +26,10 @@ def tracked_hf_hub_download(*args, **kwargs):
if filename.endswith(".pth"): if filename.endswith(".pth"):
msg = f"\nDownloading model '{filename}' from Hugging Face ({repo_id}). This may take a while. Please wait..." msg = f"\nDownloading model '{filename}' from Hugging Face ({repo_id}). This may take a while. Please wait..."
if show_warning_signal_emitter: # Check if the emitter is set if show_warning_signal_emitter: # Check if the emitter is set
show_warning_signal_emitter.emit("Downloading Model", f"Downloading model '{filename}' from Hugging Face repository '{repo_id}'. This may take a while, please wait.") show_warning_signal_emitter.emit(
"Downloading Model",
f"Downloading model '{filename}' from Hugging Face repository '{repo_id}'. This may take a while, please wait.",
)
else: else:
msg = f"\nDownloading '{filename}' from Hugging Face ({repo_id}). Please wait..." msg = f"\nDownloading '{filename}' from Hugging Face ({repo_id}). Please wait..."
if log_callback: if log_callback:
@@ -32,5 +39,7 @@ def tracked_hf_hub_download(*args, **kwargs):
print(msg, flush=True) print(msg, flush=True)
return hf_hub_download(*args, **kwargs) return hf_hub_download(*args, **kwargs)
import huggingface_hub import huggingface_hub
huggingface_hub.hf_hub_download = tracked_hf_hub_download
huggingface_hub.hf_hub_download = tracked_hf_hub_download
+4 -2
View File
@@ -1,20 +1,22 @@
import gpustat import gpustat
def check(): def check():
try: try:
stats = gpustat.new_query() stats = gpustat.new_query()
except Exception: except Exception:
return False return False
nvidia_keywords = ['nvidia', 'rtx', 'gtx', 'quadro', 'tesla', 'titan', 'mx'] nvidia_keywords = ["nvidia", "rtx", "gtx", "quadro", "tesla", "titan", "mx"]
for gpu in stats.gpus: for gpu in stats.gpus:
name = gpu.name.lower() name = gpu.name.lower()
if any(keyword in name for keyword in nvidia_keywords): if any(keyword in name for keyword in nvidia_keywords):
return True return True
return False return False
if __name__ == "__main__": if __name__ == "__main__":
stats = gpustat.new_query() stats = gpustat.new_query()
for gpu in stats.gpus: for gpu in stats.gpus:
print(gpu.name) print(gpu.name)
print(check()) print(check())
+1
View File
@@ -25,6 +25,7 @@ if sys.stderr is None:
if platform.system() == "Darwin" and platform.processor() == "arm": if platform.system() == "Darwin" and platform.processor() == "arm":
os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1" os.environ["PYTORCH_ENABLE_MPS_FALLBACK"] = "1"
# Custom message handler to filter out specific Qt warnings # Custom message handler to filter out specific Qt warnings
def qt_message_handler(mode, context, message): def qt_message_handler(mode, context, message):
if "Wayland does not support QWindow::requestActivate()" in message: if "Wayland does not support QWindow::requestActivate()" in message:
+114 -52
View File
@@ -20,6 +20,7 @@ from abogen.constants import COLORS
from copy import deepcopy from copy import deepcopy
from PyQt5.QtGui import QFontMetrics from PyQt5.QtGui import QFontMetrics
class ElidedLabel(QLabel): class ElidedLabel(QLabel):
def __init__(self, text, parent=None): def __init__(self, text, parent=None):
super().__init__(text, parent) super().__init__(text, parent)
@@ -40,6 +41,7 @@ class ElidedLabel(QLabel):
def fullText(self): def fullText(self):
return self._full_text return self._full_text
class QueueListItemWidget(QWidget): class QueueListItemWidget(QWidget):
def __init__(self, file_name, char_count): def __init__(self, file_name, char_count):
super().__init__() super().__init__()
@@ -47,6 +49,7 @@ class QueueListItemWidget(QWidget):
layout.setContentsMargins(12, 0, 6, 0) layout.setContentsMargins(12, 0, 6, 0)
layout.setSpacing(0) layout.setSpacing(0)
import os import os
name_label = ElidedLabel(os.path.basename(file_name)) name_label = ElidedLabel(os.path.basename(file_name))
char_label = QLabel(f"Chars: {char_count}") char_label = QLabel(f"Chars: {char_count}")
char_label.setStyleSheet(f"color: {COLORS['LIGHT_DISABLED']};") char_label.setStyleSheet(f"color: {COLORS['LIGHT_DISABLED']};")
@@ -56,6 +59,7 @@ class QueueListItemWidget(QWidget):
layout.addWidget(char_label, 0) layout.addWidget(char_label, 0)
self.setLayout(layout) self.setLayout(layout)
class DroppableQueueListWidget(QListWidget): class DroppableQueueListWidget(QListWidget):
def __init__(self, parent_dialog): def __init__(self, parent_dialog):
super().__init__() super().__init__()
@@ -73,7 +77,7 @@ class DroppableQueueListWidget(QListWidget):
def dragEnterEvent(self, event): def dragEnterEvent(self, event):
if event.mimeData().hasUrls(): if event.mimeData().hasUrls():
for url in event.mimeData().urls(): for url in event.mimeData().urls():
if url.isLocalFile() and url.toLocalFile().lower().endswith('.txt'): if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt"):
self.drag_overlay.resize(self.size()) self.drag_overlay.resize(self.size())
self.drag_overlay.setVisible(True) self.drag_overlay.setVisible(True)
event.acceptProposedAction() event.acceptProposedAction()
@@ -84,7 +88,7 @@ class DroppableQueueListWidget(QListWidget):
def dragMoveEvent(self, event): def dragMoveEvent(self, event):
if event.mimeData().hasUrls(): if event.mimeData().hasUrls():
for url in event.mimeData().urls(): for url in event.mimeData().urls():
if url.isLocalFile() and url.toLocalFile().lower().endswith('.txt'): if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt"):
event.acceptProposedAction() event.acceptProposedAction()
return return
event.ignore() event.ignore()
@@ -96,7 +100,11 @@ class DroppableQueueListWidget(QListWidget):
def dropEvent(self, event): def dropEvent(self, event):
self.drag_overlay.setVisible(False) self.drag_overlay.setVisible(False)
if event.mimeData().hasUrls(): if event.mimeData().hasUrls():
file_paths = [url.toLocalFile() for url in event.mimeData().urls() if url.isLocalFile() and url.toLocalFile().lower().endswith('.txt')] file_paths = [
url.toLocalFile()
for url in event.mimeData().urls()
if url.isLocalFile() and url.toLocalFile().lower().endswith(".txt")
]
if file_paths: if file_paths:
self.parent_dialog.add_files_from_paths(file_paths) self.parent_dialog.add_files_from_paths(file_paths)
event.acceptProposedAction() event.acceptProposedAction()
@@ -107,14 +115,17 @@ class DroppableQueueListWidget(QListWidget):
def resizeEvent(self, event): def resizeEvent(self, event):
super().resizeEvent(event) super().resizeEvent(event)
if hasattr(self, 'drag_overlay'): if hasattr(self, "drag_overlay"):
self.drag_overlay.resize(self.size()) self.drag_overlay.resize(self.size())
class QueueManager(QDialog): class QueueManager(QDialog):
def __init__(self, parent, queue: list, title="Queue Manager", size=(600, 700)): def __init__(self, parent, queue: list, title="Queue Manager", size=(600, 700)):
super().__init__() super().__init__()
self.queue = queue self.queue = queue
self._original_queue = deepcopy(queue) # Store a deep copy of the original queue self._original_queue = deepcopy(
queue
) # Store a deep copy of the original queue
self.parent = parent self.parent = parent
layout = QVBoxLayout() layout = QVBoxLayout()
layout.setContentsMargins(15, 15, 15, 15) # set main layout margins layout.setContentsMargins(15, 15, 15, 15) # set main layout margins
@@ -141,10 +152,12 @@ class QueueManager(QDialog):
# Overlay label for empty queue # Overlay label for empty queue
self.empty_overlay = QLabel( self.empty_overlay = QLabel(
"Drag and drop your text files here or use the 'Add files' button.", "Drag and drop your text files here or use the 'Add files' button.",
self.listwidget self.listwidget,
) )
self.empty_overlay.setAlignment(Qt.AlignCenter) self.empty_overlay.setAlignment(Qt.AlignCenter)
self.empty_overlay.setStyleSheet(f"color: {COLORS['LIGHT_DISABLED']}; background: transparent; padding: 20px;") self.empty_overlay.setStyleSheet(
f"color: {COLORS['LIGHT_DISABLED']}; background: transparent; padding: 20px;"
)
self.empty_overlay.setWordWrap(True) self.empty_overlay.setWordWrap(True)
self.empty_overlay.setAttribute(Qt.WA_TransparentForMouseEvents, True) self.empty_overlay.setAttribute(Qt.WA_TransparentForMouseEvents, True)
self.empty_overlay.hide() self.empty_overlay.hide()
@@ -208,13 +221,14 @@ class QueueManager(QDialog):
file_name = item.file_name file_name = item.file_name
display_name = file_name display_name = file_name
import os import os
if os.path.sep in file_name: if os.path.sep in file_name:
display_name = os.path.basename(file_name) display_name = os.path.basename(file_name)
# Get icon for the file # Get icon for the file
icon = icon_provider.icon(QFileInfo(file_name)) icon = icon_provider.icon(QFileInfo(file_name))
list_item = QListWidgetItem() list_item = QListWidgetItem()
# Set tooltip with detailed info # Set tooltip with detailed info
output_folder = getattr(item, 'output_folder', '') output_folder = getattr(item, "output_folder", "")
tooltip = ( tooltip = (
f"<b>Path:</b> {file_name}<br>" f"<b>Path:</b> {file_name}<br>"
f"<b>Language:</b> {getattr(item, 'lang_code', '')}<br>" f"<b>Language:</b> {getattr(item, 'lang_code', '')}<br>"
@@ -222,7 +236,7 @@ class QueueManager(QDialog):
f"<b>Voice:</b> {getattr(item, 'voice', '')}<br>" f"<b>Voice:</b> {getattr(item, 'voice', '')}<br>"
f"<b>Save Option:</b> {getattr(item, 'save_option', '')}<br>" f"<b>Save Option:</b> {getattr(item, 'save_option', '')}<br>"
) )
if output_folder not in (None, '', 'None'): if output_folder not in (None, "", "None"):
tooltip += f"<b>Output Folder:</b> {output_folder}<br>" tooltip += f"<b>Output Folder:</b> {output_folder}<br>"
tooltip += ( tooltip += (
f"<b>Subtitle Mode:</b> {getattr(item, 'subtitle_mode', '')}<br>" f"<b>Subtitle Mode:</b> {getattr(item, 'subtitle_mode', '')}<br>"
@@ -233,7 +247,7 @@ class QueueManager(QDialog):
list_item.setToolTip(tooltip) list_item.setToolTip(tooltip)
list_item.setIcon(icon) list_item.setIcon(icon)
# Use custom widget for display # Use custom widget for display
char_count = getattr(item, 'total_char_count', 0) char_count = getattr(item, "total_char_count", 0)
widget = QueueListItemWidget(file_name, char_count) widget = QueueListItemWidget(file_name, char_count)
self.listwidget.addItem(list_item) self.listwidget.addItem(list_item)
self.listwidget.setItemWidget(list_item, widget) self.listwidget.setItemWidget(list_item, widget)
@@ -244,6 +258,7 @@ class QueueManager(QDialog):
if not items: if not items:
return return
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
# Remove by index to ensure correct mapping # Remove by index to ensure correct mapping
rows = sorted([self.listwidget.row(item) for item in items], reverse=True) rows = sorted([self.listwidget.row(item) for item in items], reverse=True)
# Warn user if removing multiple files # Warn user if removing multiple files
@@ -253,7 +268,7 @@ class QueueManager(QDialog):
"Confirm Remove", "Confirm Remove",
f"Are you sure you want to remove {len(rows)} selected items from the queue?", f"Are you sure you want to remove {len(rows)} selected items from the queue?",
QMessageBox.Yes | QMessageBox.No, QMessageBox.Yes | QMessageBox.No,
QMessageBox.No QMessageBox.No,
) )
if reply != QMessageBox.Yes: if reply != QMessageBox.Yes:
return return
@@ -265,19 +280,22 @@ class QueueManager(QDialog):
def clear_queue(self): def clear_queue(self):
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
if len(self.queue) > 1: if len(self.queue) > 1:
reply = QMessageBox.question( reply = QMessageBox.question(
self, self,
"Confirm Clear Queue", "Confirm Clear Queue",
f"Are you sure you want to clear {len(self.queue)} items from the queue?", f"Are you sure you want to clear {len(self.queue)} items from the queue?",
QMessageBox.Yes | QMessageBox.No, QMessageBox.Yes | QMessageBox.No,
QMessageBox.No QMessageBox.No,
) )
if reply != QMessageBox.Yes: if reply != QMessageBox.Yes:
return return
self.queue.clear() self.queue.clear()
self.listwidget.clear() self.listwidget.clear()
self.empty_overlay.resize(self.listwidget.size()) # Ensure overlay is sized correctly self.empty_overlay.resize(
self.listwidget.size()
) # Ensure overlay is sized correctly
self.empty_overlay.show() # Show the overlay when queue is empty self.empty_overlay.show() # Show the overlay when queue is empty
self.update_button_states() self.update_button_states()
@@ -290,56 +308,74 @@ class QueueManager(QDialog):
parent = self.parent parent = self.parent
if parent is not None: if parent is not None:
# lang_code: use parent's get_voice_formula and get_selected_lang # lang_code: use parent's get_voice_formula and get_selected_lang
if hasattr(parent, 'get_voice_formula') and hasattr(parent, 'get_selected_lang'): if hasattr(parent, "get_voice_formula") and hasattr(
parent, "get_selected_lang"
):
voice_formula = parent.get_voice_formula() voice_formula = parent.get_voice_formula()
attrs['lang_code'] = parent.get_selected_lang(voice_formula) attrs["lang_code"] = parent.get_selected_lang(voice_formula)
attrs['voice'] = voice_formula attrs["voice"] = voice_formula
else: else:
attrs['lang_code'] = getattr(parent, 'selected_lang', '') attrs["lang_code"] = getattr(parent, "selected_lang", "")
attrs['voice'] = getattr(parent, 'selected_voice', '') attrs["voice"] = getattr(parent, "selected_voice", "")
# speed # speed
if hasattr(parent, 'speed_slider'): if hasattr(parent, "speed_slider"):
attrs['speed'] = parent.speed_slider.value() / 100.0 attrs["speed"] = parent.speed_slider.value() / 100.0
else: else:
attrs['speed'] = getattr(parent, 'speed', 1.0) attrs["speed"] = getattr(parent, "speed", 1.0)
# save_option # save_option
attrs['save_option'] = getattr(parent, 'save_option', '') attrs["save_option"] = getattr(parent, "save_option", "")
# output_folder # output_folder
attrs['output_folder'] = getattr(parent, 'selected_output_folder', '') attrs["output_folder"] = getattr(parent, "selected_output_folder", "")
# subtitle_mode # subtitle_mode
if hasattr(parent, 'get_actual_subtitle_mode'): if hasattr(parent, "get_actual_subtitle_mode"):
attrs['subtitle_mode'] = parent.get_actual_subtitle_mode() attrs["subtitle_mode"] = parent.get_actual_subtitle_mode()
else: else:
attrs['subtitle_mode'] = getattr(parent, 'subtitle_mode', '') attrs["subtitle_mode"] = getattr(parent, "subtitle_mode", "")
# output_format # output_format
attrs['output_format'] = getattr(parent, 'selected_format', '') attrs["output_format"] = getattr(parent, "selected_format", "")
# total_char_count # total_char_count
attrs['total_char_count'] = getattr(parent, 'char_count', '') attrs["total_char_count"] = getattr(parent, "char_count", "")
# replace_single_newlines # replace_single_newlines
attrs['replace_single_newlines'] = getattr(parent, 'replace_single_newlines', False) attrs["replace_single_newlines"] = getattr(
parent, "replace_single_newlines", False
)
else: else:
# fallback: empty values # fallback: empty values
attrs = {k: '' for k in [ attrs = {
'lang_code', 'speed', 'voice', 'save_option', k: ""
'output_folder', 'subtitle_mode', 'output_format', 'total_char_count', 'replace_single_newlines']} for k in [
"lang_code",
"speed",
"voice",
"save_option",
"output_folder",
"subtitle_mode",
"output_format",
"total_char_count",
"replace_single_newlines",
]
}
return attrs return attrs
def add_files_from_paths(self, file_paths): def add_files_from_paths(self, file_paths):
from abogen.utils import calculate_text_length from abogen.utils import calculate_text_length
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
import os import os
current_attrs = self.get_current_attributes() current_attrs = self.get_current_attributes()
duplicates = [] duplicates = []
for file_path in file_paths: for file_path in file_paths:
class QueueItem: class QueueItem:
pass pass
item = QueueItem() item = QueueItem()
item.file_name = file_path item.file_name = file_path
for attr, value in current_attrs.items(): for attr, value in current_attrs.items():
setattr(item, attr, value) setattr(item, attr, value)
# Read file content and calculate total_char_count using calculate_text_length # Read file content and calculate total_char_count using calculate_text_length
try: try:
with open(file_path, 'r', encoding='utf-8', errors='ignore') as f: with open(file_path, "r", encoding="utf-8", errors="ignore") as f:
file_content = f.read() file_content = f.read()
item.total_char_count = calculate_text_length(file_content) item.total_char_count = calculate_text_length(file_content)
except Exception: except Exception:
@@ -348,16 +384,26 @@ class QueueManager(QDialog):
is_duplicate = False is_duplicate = False
for queued_item in self.queue: for queued_item in self.queue:
if ( if (
getattr(queued_item, 'file_name', None) == getattr(item, 'file_name', None) and getattr(queued_item, "file_name", None)
getattr(queued_item, 'lang_code', None) == getattr(item, 'lang_code', None) and == getattr(item, "file_name", None)
getattr(queued_item, 'speed', None) == getattr(item, 'speed', None) and and getattr(queued_item, "lang_code", None)
getattr(queued_item, 'voice', None) == getattr(item, 'voice', None) and == getattr(item, "lang_code", None)
getattr(queued_item, 'save_option', None) == getattr(item, 'save_option', None) and and getattr(queued_item, "speed", None)
getattr(queued_item, 'output_folder', None) == getattr(item, 'output_folder', None) and == getattr(item, "speed", None)
getattr(queued_item, 'subtitle_mode', None) == getattr(item, 'subtitle_mode', None) and and getattr(queued_item, "voice", None)
getattr(queued_item, 'output_format', None) == getattr(item, 'output_format', None) and == getattr(item, "voice", None)
getattr(queued_item, 'total_char_count', None) == getattr(item, 'total_char_count', None) and and getattr(queued_item, "save_option", None)
getattr(queued_item, 'replace_single_newlines', False) == getattr(item, 'replace_single_newlines', False) == getattr(item, "save_option", None)
and getattr(queued_item, "output_folder", None)
== getattr(item, "output_folder", None)
and getattr(queued_item, "subtitle_mode", None)
== getattr(item, "subtitle_mode", None)
and getattr(queued_item, "output_format", None)
== getattr(item, "output_format", None)
and getattr(queued_item, "total_char_count", None)
== getattr(item, "total_char_count", None)
and getattr(queued_item, "replace_single_newlines", False)
== getattr(item, "replace_single_newlines", False)
): ):
is_duplicate = True is_duplicate = True
break break
@@ -369,7 +415,7 @@ class QueueManager(QDialog):
QMessageBox.warning( QMessageBox.warning(
self, self,
"Duplicate Item(s)", "Duplicate Item(s)",
f"Skipping {len(duplicates)} file(s) with the same attributes, already in the queue." f"Skipping {len(duplicates)} file(s) with the same attributes, already in the queue.",
) )
self.process_queue() self.process_queue()
self.update_button_states() self.update_button_states()
@@ -377,20 +423,23 @@ class QueueManager(QDialog):
def add_more_files(self): def add_more_files(self):
from PyQt5.QtWidgets import QFileDialog from PyQt5.QtWidgets import QFileDialog
from abogen.utils import calculate_text_length # import the function from abogen.utils import calculate_text_length # import the function
# Only allow .txt files # Only allow .txt files
files, _ = QFileDialog.getOpenFileNames(self, "Select .txt files", "", "Text Files (*.txt)") files, _ = QFileDialog.getOpenFileNames(
self, "Select .txt files", "", "Text Files (*.txt)"
)
if not files: if not files:
return return
self.add_files_from_paths(files) self.add_files_from_paths(files)
def resizeEvent(self, event): def resizeEvent(self, event):
super().resizeEvent(event) super().resizeEvent(event)
if hasattr(self, 'empty_overlay'): if hasattr(self, "empty_overlay"):
self.empty_overlay.resize(self.listwidget.size()) self.empty_overlay.resize(self.listwidget.size())
def update_button_states(self): def update_button_states(self):
# Enable Remove if at least one item is selected, else disable # Enable Remove if at least one item is selected, else disable
if hasattr(self, 'remove_button'): if hasattr(self, "remove_button"):
selected_count = len(self.listwidget.selectedItems()) selected_count = len(self.listwidget.selectedItems())
self.remove_button.setEnabled(selected_count > 0) self.remove_button.setEnabled(selected_count > 0)
if selected_count > 1: if selected_count > 1:
@@ -398,7 +447,7 @@ class QueueManager(QDialog):
else: else:
self.remove_button.setText("Remove selected") self.remove_button.setText("Remove selected")
# Disable Clear if queue is empty # Disable Clear if queue is empty
if hasattr(self, 'clear_button'): if hasattr(self, "clear_button"):
self.clear_button.setEnabled(bool(self.queue)) self.clear_button.setEnabled(bool(self.queue))
def show_context_menu(self, pos): def show_context_menu(self, pos):
@@ -406,6 +455,7 @@ class QueueManager(QDialog):
from PyQt5.QtGui import QDesktopServices from PyQt5.QtGui import QDesktopServices
from PyQt5.QtCore import QUrl from PyQt5.QtCore import QUrl
import os import os
global_pos = self.listwidget.viewport().mapToGlobal(pos) global_pos = self.listwidget.viewport().mapToGlobal(pos)
selected_items = self.listwidget.selectedItems() selected_items = self.listwidget.selectedItems()
menu = QMenu(self) menu = QMenu(self)
@@ -417,35 +467,45 @@ class QueueManager(QDialog):
# Add Open file action # Add Open file action
open_file_action = QAction("Open file", self) open_file_action = QAction("Open file", self)
def open_file(): def open_file():
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
item = selected_items[0] item = selected_items[0]
display_name = item.text() display_name = item.text()
for q in self.queue: for q in self.queue:
if os.path.basename(q.file_name) == display_name: if os.path.basename(q.file_name) == display_name:
if not os.path.exists(q.file_name): if not os.path.exists(q.file_name):
QMessageBox.warning(self, "File Not Found", f"The file does not exist.") QMessageBox.warning(
self, "File Not Found", f"The file does not exist."
)
return return
QDesktopServices.openUrl(QUrl.fromLocalFile(q.file_name)) QDesktopServices.openUrl(QUrl.fromLocalFile(q.file_name))
break break
open_file_action.triggered.connect(open_file) open_file_action.triggered.connect(open_file)
menu.addAction(open_file_action) menu.addAction(open_file_action)
# Add Go to folder action # Add Go to folder action
go_to_folder_action = QAction("Go to folder", self) go_to_folder_action = QAction("Go to folder", self)
def go_to_folder(): def go_to_folder():
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
item = selected_items[0] item = selected_items[0]
display_name = item.text() display_name = item.text()
for q in self.queue: for q in self.queue:
if os.path.basename(q.file_name) == display_name: if os.path.basename(q.file_name) == display_name:
if not os.path.exists(q.file_name): if not os.path.exists(q.file_name):
QMessageBox.warning(self, "File Not Found", f"The file does not exist.") QMessageBox.warning(
self, "File Not Found", f"The file does not exist."
)
return return
folder = os.path.dirname(q.file_name) folder = os.path.dirname(q.file_name)
if os.path.exists(folder): if os.path.exists(folder):
QDesktopServices.openUrl(QUrl.fromLocalFile(folder)) QDesktopServices.openUrl(QUrl.fromLocalFile(folder))
break break
go_to_folder_action.triggered.connect(go_to_folder) go_to_folder_action.triggered.connect(go_to_folder)
menu.addAction(go_to_folder_action) menu.addAction(go_to_folder_action)
@@ -466,6 +526,7 @@ class QueueManager(QDialog):
def reject(self): def reject(self):
# Cancel: restore original queue # Cancel: restore original queue
from PyQt5.QtWidgets import QMessageBox from PyQt5.QtWidgets import QMessageBox
# Warn if user changed a lot (e.g., more than 1 items difference) # Warn if user changed a lot (e.g., more than 1 items difference)
original_count = len(self._original_queue) original_count = len(self._original_queue)
current_count = len(self.queue) current_count = len(self.queue)
@@ -475,7 +536,7 @@ class QueueManager(QDialog):
"Confirm Cancel", "Confirm Cancel",
f"Are you sure you want to cancel and discard all changes?", f"Are you sure you want to cancel and discard all changes?",
QMessageBox.Yes | QMessageBox.No, QMessageBox.Yes | QMessageBox.No,
QMessageBox.No QMessageBox.No,
) )
if reply != QMessageBox.Yes: if reply != QMessageBox.Yes:
return return
@@ -485,7 +546,8 @@ class QueueManager(QDialog):
def keyPressEvent(self, event): def keyPressEvent(self, event):
from PyQt5.QtCore import Qt from PyQt5.QtCore import Qt
if event.key() == Qt.Key_Delete: if event.key() == Qt.Key_Delete:
self.remove_item() self.remove_item()
else: else:
super().keyPressEvent(event) super().keyPressEvent(event)
+2 -1
View File
@@ -1,6 +1,7 @@
# represents a queued item - book, chapters, voice, etc. # represents a queued item - book, chapters, voice, etc.
from dataclasses import dataclass from dataclasses import dataclass
@dataclass @dataclass
class QueuedItem: class QueuedItem:
file_name: str file_name: str
@@ -12,4 +13,4 @@ class QueuedItem:
subtitle_mode: str subtitle_mode: str
output_format: str output_format: str
total_char_count: int total_char_count: int
replace_single_newlines: bool = False replace_single_newlines: bool = False
+29 -15
View File
@@ -105,19 +105,21 @@ def clean_text(text, *args, **kwargs):
default_encoding = sys.getfilesystemencoding() default_encoding = sys.getfilesystemencoding()
def create_process(cmd, stdin=None, text=True, capture_output=False): def create_process(cmd, stdin=None, text=True, capture_output=False):
import logging import logging
logger = logging.getLogger(__name__) logger = logging.getLogger(__name__)
# Configure root logger to output to console if not already configured # Configure root logger to output to console if not already configured
root = logging.getLogger() root = logging.getLogger()
if not root.handlers: if not root.handlers:
handler = logging.StreamHandler(sys.stdout) handler = logging.StreamHandler(sys.stdout)
formatter = logging.Formatter('%(message)s') formatter = logging.Formatter("%(message)s")
handler.setFormatter(formatter) handler.setFormatter(formatter)
root.addHandler(handler) root.addHandler(handler)
root.setLevel(logging.INFO) root.setLevel(logging.INFO)
# Determine shell usage: use shell only for string commands # Determine shell usage: use shell only for string commands
use_shell = isinstance(cmd, str) use_shell = isinstance(cmd, str)
kwargs = { kwargs = {
@@ -151,11 +153,12 @@ def create_process(cmd, stdin=None, text=True, capture_output=False):
# Print the command being executed # Print the command being executed
print(f"Executing: {cmd if isinstance(cmd, str) else ' '.join(cmd)}") print(f"Executing: {cmd if isinstance(cmd, str) else ' '.join(cmd)}")
proc = subprocess.Popen(cmd, **kwargs) proc = subprocess.Popen(cmd, **kwargs)
# Stream output to console in real-time if not capturing # Stream output to console in real-time if not capturing
if proc.stdout and not capture_output: if proc.stdout and not capture_output:
def _stream_output(stream): def _stream_output(stream):
if text: if text:
# For text mode, read character by character for real-time output # For text mode, read character by character for real-time output
@@ -174,12 +177,14 @@ def create_process(cmd, stdin=None, text=True, capture_output=False):
break break
try: try:
# Try to decode binary data for display # Try to decode binary data for display
sys.stdout.write(chunk.decode(default_encoding, errors='replace')) sys.stdout.write(
chunk.decode(default_encoding, errors="replace")
)
sys.stdout.flush() sys.stdout.flush()
except Exception: except Exception:
pass pass
stream.close() stream.close()
# Start a daemon thread to handle output streaming # Start a daemon thread to handle output streaming
Thread(target=_stream_output, args=(proc.stdout,), daemon=True).start() Thread(target=_stream_output, args=(proc.stdout,), daemon=True).start()
@@ -220,6 +225,7 @@ def get_gpu_acceleration(enabled):
try: try:
import torch import torch
from torch.cuda import is_available from torch.cuda import is_available
if not enabled: if not enabled:
return "CUDA GPU available but using CPU.", False return "CUDA GPU available but using CPU.", False
if is_available(): if is_available():
@@ -227,7 +233,11 @@ def get_gpu_acceleration(enabled):
# Gather more diagnostic info if CUDA is not available # Gather more diagnostic info if CUDA is not available
try: try:
cuda_devices = torch.cuda.device_count() cuda_devices = torch.cuda.device_count()
cuda_error = torch.cuda.get_device_name(0) if cuda_devices > 0 else "No devices found" cuda_error = (
torch.cuda.get_device_name(0)
if cuda_devices > 0
else "No devices found"
)
except Exception as e: except Exception as e:
cuda_error = str(e) cuda_error = str(e)
return f"CUDA GPU is not available. Using CPU. ({cuda_error})", False return f"CUDA GPU is not available. Using CPU. ({cuda_error})", False
@@ -239,6 +249,7 @@ def prevent_sleep_start():
system = platform.system() system = platform.system()
if system == "Windows": if system == "Windows":
import ctypes import ctypes
ctypes.windll.kernel32.SetThreadExecutionState( ctypes.windll.kernel32.SetThreadExecutionState(
0x80000000 | 0x00000001 | 0x00000040 0x80000000 | 0x00000001 | 0x00000040
) )
@@ -246,19 +257,22 @@ def prevent_sleep_start():
_sleep_procs["Darwin"] = create_process(["caffeinate"]) _sleep_procs["Darwin"] = create_process(["caffeinate"])
elif system == "Linux": elif system == "Linux":
# use a sleep that never exits so inhibition stays active # use a sleep that never exits so inhibition stays active
_sleep_procs["Linux"] = create_process([ _sleep_procs["Linux"] = create_process(
"systemd-inhibit", [
"--what=handle-lid-switch:sleep", "systemd-inhibit",
"--mode=block", "--what=handle-lid-switch:sleep",
"sleep", "--mode=block",
"infinity", "sleep",
]) "infinity",
]
)
def prevent_sleep_end(): def prevent_sleep_end():
system = platform.system() system = platform.system()
if system == "Windows": if system == "Windows":
import ctypes import ctypes
ctypes.windll.kernel32.SetThreadExecutionState(0x80000000) # ES_CONTINUOUS ctypes.windll.kernel32.SetThreadExecutionState(0x80000000) # ES_CONTINUOUS
elif system in ("Darwin", "Linux") and _sleep_procs[system]: elif system in ("Darwin", "Linux") and _sleep_procs[system]:
try: try:
+15 -5
View File
@@ -230,13 +230,15 @@ class VoiceMixer(QWidget):
appstyle = QApplication.instance().style().objectName().lower() appstyle = QApplication.instance().style().objectName().lower()
if appstyle != "windowsvista": if appstyle != "windowsvista":
# Set custom groove color for disabled state using COLORS["GREY_BACKGROUND"] # Set custom groove color for disabled state using COLORS["GREY_BACKGROUND"]
self.slider.setStyleSheet(f""" self.slider.setStyleSheet(
f"""
QSlider::groove:vertical:disabled {{ QSlider::groove:vertical:disabled {{
background: {COLORS.get("GREY_BACKGROUND")}; background: {COLORS.get("GREY_BACKGROUND")};
width: 4px; width: 4px;
border-radius: 4px; border-radius: 4px;
}} }}
""") """
)
# Connect controls # Connect controls
self.slider.valueChanged.connect(lambda val: self.spin_box.setValue(val / 100)) self.slider.valueChanged.connect(lambda val: self.spin_box.setValue(val / 100))
@@ -330,7 +332,9 @@ class VoiceFormulaDialog(QDialog):
self._original_mixed_voice_state = None self._original_mixed_voice_state = None
if parent is not None: if parent is not None:
self._original_profile_name = getattr(parent, "selected_profile_name", None) self._original_profile_name = getattr(parent, "selected_profile_name", None)
self._original_mixed_voice_state = getattr(parent, "mixed_voice_state", None) self._original_mixed_voice_state = getattr(
parent, "mixed_voice_state", None
)
profiles = load_profiles() profiles = load_profiles()
self._virtual_new_profile = False self._virtual_new_profile = False
if not profiles: if not profiles:
@@ -369,7 +373,9 @@ class VoiceFormulaDialog(QDialog):
self.profile_list = QListWidget() self.profile_list = QListWidget()
self.profile_list.setSelectionMode(QListWidget.SingleSelection) self.profile_list.setSelectionMode(QListWidget.SingleSelection)
self.profile_list.setSelectionBehavior(QListWidget.SelectRows) self.profile_list.setSelectionBehavior(QListWidget.SelectRows)
self.profile_list.setStyleSheet("QListWidget::item:selected { background: palette(highlight); color: palette(highlighted-text); }") self.profile_list.setStyleSheet(
"QListWidget::item:selected { background: palette(highlight); color: palette(highlighted-text); }"
)
icon = QIcon(get_resource_path("abogen.assets", "profile.png")) icon = QIcon(get_resource_path("abogen.assets", "profile.png"))
if self._virtual_new_profile: if self._virtual_new_profile:
item = QListWidgetItem(icon, "New profile") item = QListWidgetItem(icon, "New profile")
@@ -976,6 +982,7 @@ class VoiceFormulaDialog(QDialog):
def _parse_rgba_to_qcolor(self, rgba_str): def _parse_rgba_to_qcolor(self, rgba_str):
from PyQt5.QtCore import Qt from PyQt5.QtCore import Qt
from PyQt5.QtGui import QColor from PyQt5.QtGui import QColor
"""Helper to convert 'rgba(R,G,B,A_float)' string to 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) match = re.match(r"rgba\((\d+),\s*(\d+),\s*(\d+),\s*([\d.]+)\)", rgba_str)
if match: if match:
@@ -1372,6 +1379,7 @@ class VoiceFormulaDialog(QDialog):
def update_profile_list_colors(self): def update_profile_list_colors(self):
from PyQt5.QtCore import Qt from PyQt5.QtCore import Qt
profiles = load_profiles() profiles = load_profiles()
for i in range(self.profile_list.count()): for i in range(self.profile_list.count()):
item = self.profile_list.item(i) item = self.profile_list.item(i)
@@ -1383,7 +1391,9 @@ class VoiceFormulaDialog(QDialog):
color = self._parse_rgba_to_qcolor(COLORS.get("YELLOW_BACKGROUND")) color = self._parse_rgba_to_qcolor(COLORS.get("YELLOW_BACKGROUND"))
item.setData(Qt.BackgroundRole, color) item.setData(Qt.BackgroundRole, color)
else: else:
item.setData(Qt.BackgroundRole, self.profile_list.palette().base().color()) item.setData(
Qt.BackgroundRole, self.profile_list.palette().base().color()
)
weights = profiles.get(name, {}).get("voices", []) weights = profiles.get(name, {}).get("voices", [])
total = 0 total = 0
if isinstance(weights, list): if isinstance(weights, list):
+1
View File
@@ -1,6 +1,7 @@
import re import re
from abogen.constants import VOICES_INTERNAL from abogen.constants import VOICES_INTERNAL
# Calls parsing and loads the voice to gpu or cpu # Calls parsing and loads the voice to gpu or cpu
def get_new_voice(pipeline, formula, use_gpu): def get_new_voice(pipeline, formula, use_gpu):
try: try: