Dymas/abogen
1
0
Fork 0
mirror of https://github.com/denizsafak/abogen.git synced 2026-09-20 19:50:59 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(pyqt): migrate GUI to Language enums, fix subtitle mode gating

Browse Source 
Complete the Language enum unification (commit 0dc491e) for the PyQt
GUI, which was left resolving languages from kokoro letter codes
(voice[0]) while domain and WebUI already used Language enums.

- selected_lang is now always a Language enum: voices resolve via
  language_for_voice_id(), profiles via resolve_profile_language()
- kokoro letter->Language mapping stays in the engine (new public
  language_for_code()); the Language.from_code() domain shim is removed
- legacy profile files with letter codes ("a", "e", ...) are tolerated
  only at the profile read boundary; new profiles save ISO codes
- conversion.py letter comparisons replaced with enum comparisons, and
  SynthParams lang_code= -> language= (would TypeError at runtime)
- subtitle dropdown enabled for all languages; word-count and
  highlighting modes restricted to English with auto-switch to Sentence
- tests: engine mapping + profile language resolution added; 1566 pass
This commit is contained in:
Deniz Şafak
2026-08-20 21:28:30 +03:00
parent f340b976db
commit 11274ad6bf
13 changed files with 183 additions and 68 deletions
Download Patch File Download Diff File Expand all files Collapse all files
abogen/constants.py
+6 -5
View File
@@ -70,11 +70,12 @@ SUPPORTED_INPUT_FORMATS = [
"vtt",
]
# Supported languages for subtitle generation
# Currently, only English (EN_US, EN_GB) are supported for subtitle generation.
# This is because tokens that contain timestamps are not generated for other languages in the Kokoro pipeline.
# Please refer to: https://github.com/hexgrad/kokoro/blob/6d87f4ae7abc2d14dbc4b3ef2e5f19852e861ac2/kokoro/pipeline.py
SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = [Language.EN_US, Language.EN_GB]
# Supported languages for subtitle generation.
# All languages are supported: only English emits per-word timestamped tokens
# in the Kokoro pipeline, but other languages fall back to segment-level fake
# tokens (see abogen.domain.tokens.FakeToken), so subtitles are still
# generated at segment granularity.
SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION = list(Language)
# Voice and sample text mapping
SAMPLE_VOICE_TEXTS = {
abogen/domain/conversion_pipeline.py
+2 -4
View File
@@ -112,12 +112,10 @@ def spacy_pre_tts_segmentation(
def _to_language_enum(lang_code: Any) -> Language:
"""Convert lang_code to Language enum."""
if isinstance(lang_code, Language):
return lang_code
"""Convert lang_code to Language enum (ISO code or Language enum)."""
try:
return Language.from_str(str(lang_code))
except (ValueError, AttributeError):
except ValueError:
return Language.EN_US
abogen/domain/enums.py
+6 -2
View File
@@ -212,8 +212,12 @@ class Language(str, Enum):
@property
def supports_subtitle_tokens(self) -> bool:
"""True if this language generates timestamped tokens for subtitles."""
return self in (self.EN_US, self.EN_GB)
"""True if this language supports subtitle generation.
All languages are supported: languages without per-word timestamped
tokens fall back to segment-level fake tokens in the pipeline.
"""
return True
@classmethod
def from_str(cls, value: str) -> Language:
abogen/domain/split_pattern.py
+1 -1
View File
@@ -16,7 +16,7 @@ def get_split_pattern(language: Language, subtitle_mode: str) -> str:
"""Get the appropriate split pattern based on language and subtitle mode.
Args:
language: Language enum value.
language: Language enum value, ISO code, or kokoro letter code.
subtitle_mode: Subtitle mode ("Sentence", "Sentence + Comma", "Line", etc.)
Returns:
abogen/pyqt/conversion.py
+5 -4
View File
@@ -22,6 +22,7 @@ from abogen.constants import (
)
from abogen.infrastructure.subtitle_writer import make_subtitle_writer, resolve_subtitle_format
from abogen.domain.split_pattern import get_split_pattern
from abogen.domain.enums import Language
from abogen.domain.subtitle_processor import (
parse_subtitle_file,
process_subtitle_entries,
@@ -872,12 +873,12 @@ class ConversionThread(QThread):
)
spacy_sentences = None
active_split_pattern = self.split_pattern
spacing_pattern = r"\s*" if self.lang_code in ["z", "j"] else r"\s+"
spacing_pattern = r"\s*" if self.lang_code in (Language.JA, Language.ZH) else r"\s+"
# Pre-load spaCy model for English if it will be needed for subtitle generation
if (
use_spacy
and self.lang_code in ["a", "b"]
and self.lang_code in (Language.EN_US, Language.EN_GB)
and self.subtitle_mode in ["Sentence", "Sentence + Comma"]
):
from abogen.spacy_utils import get_spacy_model
@@ -894,7 +895,7 @@ class ConversionThread(QThread):
)
)
if use_spacy and self.lang_code not in ["a", "b"]:
if use_spacy and self.lang_code not in (Language.EN_US, Language.EN_GB):
# Non-English: use spaCy for pre-TTS segmentation
self.log_updated.emit(
("\nUsing spaCy for sentence segmentation (pre-TTS)...", "grey")
@@ -1011,7 +1012,7 @@ class ConversionThread(QThread):
audio_sink=merged_sink if merge_chapters_at_end else None,
subtitle_mode=self.subtitle_mode,
max_subtitle_words=self.max_subtitle_words,
lang_code=self.lang_code,
language=self.lang_code,
use_spacy_segmentation=getattr(self, "use_spacy_segmentation", False),
)
abogen/pyqt/gui.py
+41 -39
View File
@@ -75,6 +75,7 @@ from abogen.domain.text_utils import calculate_text_length
from abogen.pyqt.conversion import ConversionThread, VoicePreviewThread, PlayAudioThread, ChapterOptionsDialog, TimestampDetectionDialog
from abogen.pyqt.book_handler import HandlerDialog
from abogen.domain.enums import Language
from abogen.constants import (
PROGRAM_NAME,
VERSION,
@@ -88,8 +89,9 @@ from abogen.constants import (
from abogen.tts_plugin.utils import get_voices
import threading
from abogen.pyqt.voice_formula_gui import VoiceFormulaDialog
from abogen.voice_profiles import load_profiles
from abogen.voice_profiles import load_profiles, resolve_profile_language
from abogen.domain.settings_core import all_settings_defaults
from plugins.kokoro.engine import language_for_code, language_for_voice_id
# Module-level default cache for use outside __init__
_DEFAULTS = all_settings_defaults()
@@ -397,11 +399,7 @@ class InputBox(QLabel):
# Re-enable subtitle and replace newlines controls when cleared
window = self.window()
if hasattr(window, "subtitle_combo"):
# Only enable if language supports it
current_lang = getattr(window, "selected_lang", "a")
window.subtitle_combo.setEnabled(
current_lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
)
window.subtitle_combo.setEnabled(True)
if hasattr(window, "replace_newlines_combo"):
window.replace_newlines_combo.setEnabled(True)
@@ -941,7 +939,7 @@ class abogen(QWidget):
self.selected_lang = None
else:
self.selected_voice = self.config.get("selected_voice", _d["selected_voice"])
self.selected_lang = self.selected_voice[0] if self.selected_voice else None
self.selected_lang = language_for_voice_id(self.selected_voice)
self.is_converting = False
self.subtitle_mode = self.config.get("subtitle_mode", _d["subtitle_mode"])
self.max_subtitle_words = self.config.get("max_subtitle_words", _d["max_subtitle_words"])
@@ -1012,10 +1010,12 @@ class abogen(QWidget):
entry = load_profiles().get(self.selected_profile_name, {})
if isinstance(entry, dict):
self.mixed_voice_state = entry.get("voices", [])
self.selected_lang = entry.get("language")
self.selected_lang = resolve_profile_language(entry)
else:
self.mixed_voice_state = entry
self.selected_lang = entry[0][0] if entry and entry[0] else None
self.selected_lang = (
language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
)
if self.save_option == "Choose output folder" and self.selected_output_folder:
self.save_path_label.setText(self.selected_output_folder)
self.save_path_row_widget.show()
@@ -1181,6 +1181,7 @@ class abogen(QWidget):
"Sentence + Comma: Subtitles will be generated for each sentence and comma.\n"
"Sentence + Highlighting: Subtitles with word-by-word karaoke highlighting.\n"
"1+ word: Subtitles will be generated for each word(s).\n\n"
"Word-count and highlighting modes are only available for English.\n"
"Supported languages for subtitle generation:\n"
+ "\n".join(
f'"{lang}" => {LANGUAGE_DESCRIPTIONS.get(lang, lang)}'
@@ -1759,8 +1760,9 @@ class abogen(QWidget):
def update_subtitle_options_availability(self):
"""
Update the enabled state of subtitle options based on the selected language.
For non-English languages, only sentence-based and line-based modes are supported.
Update the enabled state of subtitle options based on the selected
language and input type. Subtitle generation works for every language,
but word-count and highlighting modes are only available for English.
"""
# Check if current file is a subtitle file
is_subtitle_input = False
@@ -1769,16 +1771,14 @@ class abogen(QWidget):
):
is_subtitle_input = True
if self.selected_lang not in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION:
self.subtitle_combo.setEnabled(False)
self.subtitle_format_combo.setEnabled(False)
return
# Only enable subtitle_combo if it's NOT a subtitle input
self.subtitle_combo.setEnabled(not is_subtitle_input)
self.subtitle_format_combo.setEnabled(True)
is_english = self.selected_lang in ["a", "b"]
is_english = self.selected_lang in (
Language.EN_US,
Language.EN_GB,
)
# Items to keep enabled for non-English
allowed_modes = ["Disabled", "Line", "Sentence", "Sentence + Comma"]
@@ -1793,10 +1793,7 @@ class abogen(QWidget):
if is_english:
item.setEnabled(True)
else:
if text in allowed_modes:
item.setEnabled(True)
else:
item.setEnabled(False)
item.setEnabled(text in allowed_modes)
# If current selection is disabled, switch to a valid one
current_text = self.subtitle_combo.currentText()
@@ -1815,7 +1812,7 @@ class abogen(QWidget):
def on_voice_changed(self, index):
voice = self.voice_combo.itemData(index)
self.selected_voice, self.selected_lang = voice, voice[0]
self.selected_voice, self.selected_lang = voice, language_for_voice_id(voice)
self.config["selected_voice"] = voice
save_config(self.config)
# Enable/disable subtitle options based on language
@@ -1832,10 +1829,12 @@ class abogen(QWidget):
# set mixed voices and language
if isinstance(entry, dict):
self.mixed_voice_state = entry.get("voices", [])
self.selected_lang = entry.get("language")
self.selected_lang = resolve_profile_language(entry)
else:
self.mixed_voice_state = entry
self.selected_lang = entry[0][0] if entry and entry[0] else None
self.selected_lang = (
language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
)
self.selected_voice = None
self.config["selected_profile_name"] = pname
self.config.pop("selected_voice", None)
@@ -1845,7 +1844,7 @@ class abogen(QWidget):
else:
self.mixed_voice_state = None
self.selected_profile_name = None
self.selected_voice, self.selected_lang = data, data[0]
self.selected_voice, self.selected_lang = data, language_for_voice_id(data)
self.config["selected_voice"] = data
if "selected_profile_name" in self.config:
del self.config["selected_profile_name"]
@@ -1856,8 +1855,9 @@ class abogen(QWidget):
from abogen.voice_profiles import load_profiles
entry = load_profiles().get(profile_name, {})
lang = entry.get("language") if isinstance(entry, dict) else None
enable = lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
enable = (
resolve_profile_language(entry) in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
)
self.subtitle_combo.setEnabled(enable)
self.subtitle_format_combo.setEnabled(enable)
@@ -2239,18 +2239,18 @@ class abogen(QWidget):
else:
return self.selected_voice
def get_selected_lang(self, voice_formula) -> str:
def get_selected_lang(self, voice_formula) -> Language:
if self.selected_profile_name:
from abogen.voice_profiles import load_profiles
entry = load_profiles().get(self.selected_profile_name, {})
selected_lang = entry.get("language")
selected_lang = resolve_profile_language(entry)
else:
selected_lang = self.selected_voice[0] if self.selected_voice else None
selected_lang = language_for_voice_id(self.selected_voice)
# fallback: extract from formula if missing
if not selected_lang:
m = re.search(r"\b([a-z])", voice_formula)
selected_lang = m.group(1) if m else None
selected_lang = language_for_code(m.group(1)) if m else Language.EN_US
return selected_lang
def get_actual_subtitle_mode(self) -> str:
@@ -2426,7 +2426,7 @@ class abogen(QWidget):
self.update_log((gpu_msg, gpu_ok))
self.update_log("Loading modules...")
lang_code = self.selected_lang or "a"
lang_code = self.selected_lang or Language.EN_US
load_thread = LoadPipelineThread(
pipeline_loaded_callback, lang_code=lang_code, use_gpu=gpu_ok
)
@@ -2757,12 +2757,12 @@ class abogen(QWidget):
from abogen.voice_profiles import load_profiles
entry = load_profiles().get(self.selected_profile_name, {})
lang_to_cache = entry.get("language")
lang_to_cache = resolve_profile_language(entry)
else:
lang_to_cache = self.selected_lang
if not lang_to_cache and self.mixed_voice_state:
lang_to_cache = (
self.mixed_voice_state[0][0][0]
language_for_voice_id(self.mixed_voice_state[0][0])
if self.mixed_voice_state and self.mixed_voice_state[0][0]
else None
)
@@ -2866,7 +2866,7 @@ class abogen(QWidget):
)
self.loading_movie.start()
lang = self.selected_lang or "a"
lang = self.selected_lang or Language.EN_US
load_thread = LoadPipelineThread(
self._on_pipeline_loaded_for_preview, lang_code=lang, use_gpu=self.gpu_ok
)
@@ -2898,17 +2898,17 @@ class abogen(QWidget):
from abogen.voice_profiles import load_profiles
entry = load_profiles().get(self.selected_profile_name, {})
lang = entry.get("language")
lang = resolve_profile_language(entry)
else:
lang = self.selected_lang
if not lang and self.mixed_voice_state:
lang = (
self.mixed_voice_state[0][0][0]
language_for_voice_id(self.mixed_voice_state[0][0])
if self.mixed_voice_state and self.mixed_voice_state[0][0]
else None
)
else:
lang = self.selected_voice[0]
lang = language_for_voice_id(self.selected_voice)
voice = self.selected_voice
# use same gpu/cpu logic as in conversion
@@ -3954,7 +3954,9 @@ Categories=AudioVideo;Audio;Utility;
initial_state = entry.get("voices", [])
else:
initial_state = entry
self.selected_lang = entry[0][0] if entry and entry[0] else None
self.selected_lang = (
language_for_voice_id(entry[0]) if entry and entry[0] else Language.EN_US
)
dialog = VoiceFormulaDialog(
self, initial_state=initial_state, selected_profile=selected_profile
)
abogen/pyqt/voice_formula_gui.py
+7 -5
View File
@@ -28,7 +28,6 @@ from PyQt6.QtWidgets import (
from PyQt6.QtCore import Qt, QTimer, QPoint, QRect, QSize
from PyQt6.QtGui import QPixmap, QIcon, QAction
from abogen.constants import (
SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION,
LANGUAGE_DESCRIPTIONS,
COLORS,
)
@@ -949,7 +948,9 @@ class VoiceFormulaDialog(QDialog):
lang = state.get("language") if isinstance(state, dict) else None
# apply language selection
if lang:
i = self.language_combo.findData(lang)
from abogen.voice_profiles import resolve_profile_language
i = self.language_combo.findData(resolve_profile_language(state))
if i >= 0:
self.language_combo.blockSignals(True)
self.language_combo.setCurrentIndex(i)
@@ -1571,9 +1572,10 @@ class VoiceFormulaDialog(QDialog):
parent.selected_profile_name = None
lang = self.language_combo.currentData()
parent.selected_lang = lang
parent.subtitle_combo.setEnabled(
lang in SUPPORTED_LANGUAGES_FOR_SUBTITLE_GENERATION
)
if hasattr(parent, "update_subtitle_options_availability"):
parent.update_subtitle_options_availability()
else:
parent.subtitle_combo.setEnabled(True)
# Reset start flag and trigger preview
self._started = False
parent.preview_voice()
abogen/spacy_utils.py
+3 -1
View File
@@ -57,7 +57,9 @@ def get_spacy_model(language: Language, log_callback=None):
print(msg)
if not isinstance(language, Language):
raise TypeError(f"language must be Language enum, got {type(language).__name__}: {language!r}")
raise TypeError(
f"language must be Language enum, got {type(language).__name__}: {language!r}"
)
if language in _nlp_cache:
return _nlp_cache[language]
abogen/voice_profiles.py
+24 -1
View File
@@ -2,6 +2,7 @@ import json
import os
from typing import Any, Dict, Iterable, List, Tuple
from abogen.domain.enums import Language
from abogen.tts_plugin.utils import get_voices, is_plugin_registered
from abogen.utils import get_user_config_path
@@ -176,13 +177,35 @@ def save_profile(name: str, *, language: str, voices: Iterable) -> None:
raise ValueError("At least one voice with a weight above zero is required")
if not language:
language = "a"
language = Language.EN_US
profiles = load_profiles()
profiles[name] = {"provider": "kokoro", "language": language, "voices": normalized}
save_profiles(profiles)
def resolve_profile_language(entry: Any) -> Language:
"""Resolve a profile's stored language to a Language enum.
New profiles store ISO codes (Language enum values); legacy profiles may
store kokoro letter codes ("a", "b", ...). Unparseable values fall back
to EN_US.
"""
raw = entry.get("language") if isinstance(entry, dict) else None
if isinstance(raw, Language):
return raw
text = str(raw or "").strip()
if not text:
return Language.EN_US
try:
return Language.from_str(text)
except ValueError:
from plugins.kokoro.engine import language_for_code
return language_for_code(text)
def remove_profile(name: str) -> None:
delete_profile(name)