mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
James Pine
3584283d84
Add Kokoro-82M as a new TTS engine — 82M params, CPU realtime, 8 languages, Apache 2.0. Unlike cloning engines, Kokoro uses pre-built voice styles, which required a new profile type system to support non-cloning engines cleanly. Kokoro engine: - New kokoro_backend.py implementing TTSBackend protocol - 50 built-in voices across en/es/fr/hi/it/pt/ja/zh - KPipeline API with language-aware G2P routing via misaki - PyInstaller bundling for misaki, language_tags, espeakng_loader, en_core_web_sm Voice profile type system: - New voice_type column: 'cloned' | 'preset' | 'designed' (future) - Preset profiles store engine + voice ID instead of audio samples - default_engine field on profiles — auto-selects engine on profile pick - Create Voice dialog: toggle between 'Clone from audio' and 'Built-in voice' - Edit dialog shows preset voice info instead of sample list for preset profiles - Engine selector locks to preset engine when preset profile is selected - Profile grid filters by engine — shows Kokoro voices when Kokoro selected - Custom empty state when no preset profiles exist for selected engine Bug fixes: - Fix relative audio paths in DB causing 404s in production builds - config.set_data_dir() now resolves to absolute paths - Startup migration converts existing relative paths to absolute Also updates PROJECT_STATUS.md and tts-engines.mdx developer guide.
86 lines
4.6 KiB
RPMSpec
86 lines
4.6 KiB
RPMSpec
# -*- mode: python ; coding: utf-8 -*-
|
|
from PyInstaller.utils.hooks import collect_submodules
|
|
from PyInstaller.utils.hooks import collect_all
|
|
from PyInstaller.utils.hooks import copy_metadata
|
|
|
|
datas = []
|
|
binaries = []
|
|
hiddenimports = ['backend', 'backend.main', 'backend.config', 'backend.database', 'backend.models', 'backend.services.profiles', 'backend.services.history', 'backend.services.tts', 'backend.services.transcribe', 'backend.utils.platform_detect', 'backend.backends', 'backend.backends.pytorch_backend', 'backend.utils.audio', 'backend.utils.cache', 'backend.utils.progress', 'backend.utils.hf_progress', 'backend.services.cuda', 'backend.services.effects', 'backend.utils.effects', 'backend.services.versions', 'pedalboard', 'chatterbox', 'chatterbox.tts_turbo', 'chatterbox.mtl_tts', 'backend.backends.chatterbox_backend', 'backend.backends.chatterbox_turbo_backend', 'backend.backends.luxtts_backend', 'zipvoice', 'zipvoice.luxvoice', 'torch', 'transformers', 'fastapi', 'uvicorn', 'sqlalchemy', 'soundfile', 'qwen_tts', 'qwen_tts.inference', 'qwen_tts.inference.qwen3_tts_model', 'qwen_tts.inference.qwen3_tts_tokenizer', 'qwen_tts.core', 'qwen_tts.cli', 'requests', 'pkg_resources.extern', 'backend.backends.hume_backend', 'tada', 'tada.modules', 'tada.modules.tada', 'tada.modules.encoder', 'tada.modules.decoder', 'tada.modules.aligner', 'tada.modules.acoustic_spkr_verf', 'tada.nn', 'tada.nn.vibevoice', 'tada.utils', 'tada.utils.gray_code', 'tada.utils.text', 'backend.utils.dac_shim', 'torchaudio', 'backend.backends.kokoro_backend', 'kokoro', 'kokoro.pipeline', 'kokoro.model', 'kokoro.istftnet', 'kokoro.modules', 'kokoro.custom_stft', 'en_core_web_sm', 'loguru', 'backend.backends.mlx_backend', 'mlx', 'mlx.core', 'mlx.nn', 'mlx_audio', 'mlx_audio.tts', 'mlx_audio.stt']
|
|
datas += copy_metadata('qwen-tts')
|
|
datas += copy_metadata('requests')
|
|
datas += copy_metadata('transformers')
|
|
datas += copy_metadata('huggingface-hub')
|
|
datas += copy_metadata('tokenizers')
|
|
datas += copy_metadata('safetensors')
|
|
datas += copy_metadata('tqdm')
|
|
datas += copy_metadata('en_core_web_sm')
|
|
hiddenimports += collect_submodules('jaraco')
|
|
hiddenimports += collect_submodules('tada')
|
|
hiddenimports += collect_submodules('mlx')
|
|
hiddenimports += collect_submodules('mlx_audio')
|
|
tmp_ret = collect_all('zipvoice')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('linacodec')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('lazy_loader')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('librosa')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('qwen_tts')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('inflect')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('perth')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('piper_phonemize')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('misaki')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('language_tags')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('espeakng_loader')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('en_core_web_sm')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('mlx')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
tmp_ret = collect_all('mlx_audio')
|
|
datas += tmp_ret[0]; binaries += tmp_ret[1]; hiddenimports += tmp_ret[2]
|
|
|
|
|
|
a = Analysis(
|
|
['server.py'],
|
|
pathex=[],
|
|
binaries=binaries,
|
|
datas=datas,
|
|
hiddenimports=hiddenimports,
|
|
hookspath=[],
|
|
hooksconfig={},
|
|
runtime_hooks=[],
|
|
excludes=['nvidia', 'nvidia.cublas', 'nvidia.cuda_cupti', 'nvidia.cuda_nvrtc', 'nvidia.cuda_runtime', 'nvidia.cudnn', 'nvidia.cufft', 'nvidia.curand', 'nvidia.cusolver', 'nvidia.cusparse', 'nvidia.nccl', 'nvidia.nvjitlink', 'nvidia.nvtx'],
|
|
noarchive=False,
|
|
optimize=0,
|
|
)
|
|
pyz = PYZ(a.pure)
|
|
|
|
exe = EXE(
|
|
pyz,
|
|
a.scripts,
|
|
a.binaries,
|
|
a.datas,
|
|
[],
|
|
name='voicebox-server',
|
|
debug=False,
|
|
bootloader_ignore_signals=False,
|
|
strip=False,
|
|
upx=True,
|
|
upx_exclude=[],
|
|
runtime_tmpdir=None,
|
|
console=True,
|
|
disable_windowed_traceback=False,
|
|
argv_emulation=False,
|
|
target_arch=None,
|
|
codesign_identity=None,
|
|
entitlements_file=None,
|
|
)
|