fix(build): bundle kokoro source files for transformers runtime introspection

transformers opens .py source files at runtime to check attention/MoE
implementation via regex (e.g. _can_set_attn_implementation). PyInstaller's
--hidden-import only bundles .pyc bytecode, so kokoro/modules.py was missing
from the bundle causing a FileNotFoundError on Kokoro model load.

Switch from individual --hidden-import entries to --collect-all kokoro in both
build_binary.py and voicebox-server.spec. The kokoro package is 172K so no
meaningful bundle size impact.

Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>

backend/build_binary.py

@@ -241,20 +241,13 @@ def build_server(cuda=False):
             "--collect-submodules",
             "tada",
             # Kokoro 82M — lightweight TTS engine using misaki G2P
+            # collect-all is required because transformers introspects .py source
+            # files at runtime (e.g. _can_set_attn_implementation opens the class
+            # file); hidden-import alone only bundles bytecode.
             "--hidden-import",
             "backend.backends.kokoro_backend",
-            "--hidden-import",
+            "--collect-all",
             "kokoro",
-            "--hidden-import",
-            "kokoro.pipeline",
-            "--hidden-import",
-            "kokoro.model",
-            "--hidden-import",
-            "kokoro.istftnet",
-            "--hidden-import",
-            "kokoro.modules",
-            "--hidden-import",
-            "kokoro.custom_stft",
             # misaki ships G2P data files (dictionaries, phoneme tables)
             # that must be bundled for espeak/en/ja/zh G2P to work
             "--collect-all",

backend/voicebox-server.spec

@@ -5,7 +5,7 @@ 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.backends.qwen_custom_voice_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']
+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.backends.qwen_custom_voice_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', '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')
@@ -34,6 +34,8 @@ 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('kokoro')
+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')
@@ -56,7 +58,7 @@ a = Analysis(
     hiddenimports=hiddenimports,
     hookspath=[],
     hooksconfig={},
-    runtime_hooks=[],
+    runtime_hooks=['/Users/jamie/Projects/spacedriveapp/voicebox/backend/pyi_rth_numpy_compat.py'],
     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,