diff options
Diffstat (limited to 'converter/converter.py')
| -rw-r--r-- | converter/converter.py | 14 |
1 files changed, 7 insertions, 7 deletions
diff --git a/converter/converter.py b/converter/converter.py index 4da3626..3915fe4 100644 --- a/converter/converter.py +++ b/converter/converter.py @@ -18,7 +18,7 @@ from .tts import ( BACKENDS, BACKEND_AUDIOCPP, BACKEND_FASTER, - BACKEND_GRADIO, + BACKEND_QWEN, MODEL_SIZE, VOICE_MODE_CLONE, VOICE_MODE_CUSTOM, @@ -131,12 +131,12 @@ def prompt_overwrite(existing: List[Path], output_name: str) -> bool: class AudiobookConverter: - """Audiobook converter using the Qwen TTS API.""" + """Audiobook converter using a local TTS API.""" def __init__(self, voice_mode: str = VOICE_MODE_CUSTOM, voice_clone_ref_audio: Optional[str] = None, voice_clone_ref_text: Optional[str] = None, skip_transcription: bool = False, speed: float = 1.0, single_file: bool = False, output_format: str = config.AUDIO_FORMAT, - language: Optional[str] = None, backend: str = BACKEND_GRADIO, + language: Optional[str] = None, backend: str = config.BACKEND, voice: Optional[str] = None, debug: bool = False, chunk: bool = False, model_id: Optional[str] = None): if speed <= 0: @@ -158,7 +158,7 @@ class AudiobookConverter: self.backend = backend self.voice = voice self.debug = bool(debug) - # Client-side chunking: the gradio and faster backends always chunk + # Client-side chunking: the qwen and faster backends always chunk # (their servers do one generation per request and silently truncate # long text). The audio.cpp server chunks long text itself, so it # defaults to one request per chapter; --chunk forces client-side @@ -192,7 +192,7 @@ class AudiobookConverter: f"Unknown voice mode: {self.voice_mode!r} " f"(expected one of {VOICE_MODES})" ) - if self.voice_mode == VOICE_MODE_CLONE and self.backend == BACKEND_GRADIO: + if self.voice_mode == VOICE_MODE_CLONE and self.backend == BACKEND_QWEN: if not self.voice_clone_ref_audio: raise ValueError( "Voice Clone mode requires a reference audio file. " @@ -464,7 +464,7 @@ class AudiobookConverter: def _chapter_chunks(self, text: str) -> List[str]: """Split chapter text into TTS requests. - Client-side chunking splits into CHUNK_SIZE-word chunks (gradio and + Client-side chunking splits into CHUNK_SIZE-word chunks (qwen and faster always; audio.cpp only with --chunk). Otherwise (audio.cpp default) the whole text is one request and the server does its own long-form chunking. @@ -575,7 +575,7 @@ class AudiobookConverter: def _print_banner(self) -> None: """Print the startup summary for the selected backend.""" print("=" * 70) - print("QWEN-BASED AUDIOBOOK CONVERTER") + print("TTS AUDIOBOOK GENERATOR") print("=" * 70) print(f"Books folder: {BOOKS_FOLDER}") print(f"Output folder: {AUDIOBOOKS_FOLDER}") |