Initial commit: Polish AI dubbing pipeline (ComfyUI + Higgs Audio V3)
Converts SRT subtitles into a Polish lektor-style voiceover using a local
ComfyUI instance running Higgs Audio V3, then muxes the result back into the
source video as a second audio track. Video and original audio are always
stream-copied; only the new voiceover track is encoded.
Contents:
lektor_ai_comfy.py main pipeline (standard library only, needs ffmpeg)
lektor_ai_comfy_v2.py batched-context experiment (timing unresolved)
lektor_ai.py earlier version using the hosted Boson AI API
install_comfyui.sh reproduces the ComfyUI environment, versions pinned
docs/ requirements, installation, usage, architecture,
troubleshooting
gudowski/ voice references (.wav) with their transcripts (.txt)
Source media and generated video are gitignored.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
Claude Opus 5
@@ -0,0 +1,232 @@
|
||||
absl-py==2.4.0
|
||||
accelerate==1.14.0
|
||||
aiohappyeyeballs==2.6.2
|
||||
aiohttp==3.14.1
|
||||
aiosignal==1.4.0
|
||||
alembic==1.18.5
|
||||
aliyun-python-sdk-core==2.16.0
|
||||
aliyun-python-sdk-kms==2.16.5
|
||||
annotated-doc==0.0.4
|
||||
annotated-types==0.7.0
|
||||
antlr4-python3-runtime==4.9.3
|
||||
anyio==4.14.1
|
||||
attrs==26.1.0
|
||||
audioread==3.1.0
|
||||
av==17.1.0
|
||||
babel==2.18.0
|
||||
bitsandbytes==0.49.2
|
||||
blake3==1.0.9
|
||||
braceexpand==0.1.7
|
||||
certifi==2026.6.17
|
||||
cffi==2.0.0
|
||||
charset-normalizer==3.4.7
|
||||
click==8.4.2
|
||||
cn2an==0.5.24
|
||||
comfy-aimdo==0.4.10
|
||||
comfy-kitchen==0.2.12
|
||||
comfyui-embedded-docs==0.5.5
|
||||
comfyui-workflow-templates-core==0.3.263
|
||||
comfyui-workflow-templates-media-api==0.3.81
|
||||
comfyui-workflow-templates-media-image==0.3.157
|
||||
comfyui-workflow-templates-media-other==0.3.226
|
||||
comfyui-workflow-templates-media-video==0.3.98
|
||||
comfyui_frontend_package==1.45.19
|
||||
comfyui_workflow_templates==0.10.7
|
||||
conformer==0.3.2
|
||||
crcmod==1.7
|
||||
cryptography==49.0.0
|
||||
csvw==4.0.0
|
||||
cuda-bindings==12.9.4
|
||||
cuda-pathfinder==1.2.2
|
||||
cuda-toolkit==12.8.1
|
||||
Cython==3.2.6
|
||||
dacite==1.9.2
|
||||
datasets==5.0.0
|
||||
decorator==5.3.1
|
||||
dill==0.4.1
|
||||
Distance==0.1.3
|
||||
dlinfo==2.0.0
|
||||
dyNET38==2.2
|
||||
echo-tts==0.1.4
|
||||
editdistance==0.8.1
|
||||
einops==0.8.2
|
||||
einx==0.4.3
|
||||
ema-pytorch==0.7.9
|
||||
encodec==0.1.1
|
||||
faiss-cpu==1.14.3
|
||||
filelock==3.29.0
|
||||
flatbuffers==25.12.19
|
||||
frozendict==2.4.7
|
||||
frozenlist==1.8.0
|
||||
fsspec==2026.4.0
|
||||
funasr==1.3.14
|
||||
g2p-en==2.1.0
|
||||
gitdb==4.0.12
|
||||
GitPython==3.1.50
|
||||
glfw==2.10.0
|
||||
greenlet==3.5.2
|
||||
h11==0.16.0
|
||||
h5py==3.16.0
|
||||
hf-xet==1.5.1
|
||||
httpcore==1.0.9
|
||||
httpx==0.28.1
|
||||
huggingface_hub==1.21.0
|
||||
hydra-core==1.3.3
|
||||
hyper-connections==0.4.11
|
||||
HyperPyYAML==1.2.3
|
||||
idna==3.18
|
||||
inflect==7.5.0
|
||||
isodate==0.7.2
|
||||
jaconv==0.5.0
|
||||
jamo==0.4.1
|
||||
jieba==0.42.1
|
||||
Jinja2==3.1.6
|
||||
jmespath==0.10.0
|
||||
joblib==1.5.3
|
||||
json5==0.15.0
|
||||
jsonschema==4.26.0
|
||||
jsonschema-specifications==2025.9.1
|
||||
kaldiio==2.18.1
|
||||
keras==3.15.0
|
||||
kornia==0.8.3
|
||||
kornia_rs==0.1.14
|
||||
langcodes==3.5.1
|
||||
language-tags==1.3.1
|
||||
lazy-loader==0.5
|
||||
librosa==0.11.0
|
||||
lingua-language-detector==2.2.0
|
||||
llvmlite==0.47.0
|
||||
local-attention==1.11.2
|
||||
loguru==0.7.3
|
||||
Mako==1.3.12
|
||||
markdown-it-py==4.2.0
|
||||
MarkupSafe==3.0.3
|
||||
mdurl==0.1.2
|
||||
ml_dtypes==0.5.4
|
||||
modelscope==1.37.1
|
||||
monotonic-alignment-search==0.2.1
|
||||
more-itertools==11.1.0
|
||||
mpmath==1.3.0
|
||||
msgpack==1.2.1
|
||||
multidict==6.7.1
|
||||
multiprocess==0.70.19
|
||||
munch==4.0.0
|
||||
nagisa==0.2.12
|
||||
namex==0.1.0
|
||||
narwhals==2.22.1
|
||||
networkx==3.6.1
|
||||
ninja==1.13.0
|
||||
nltk==3.9.4
|
||||
numba==0.65.1
|
||||
numpy==2.2.6
|
||||
nvidia-cublas-cu12==12.8.4.1
|
||||
nvidia-cuda-cupti-cu12==12.8.90
|
||||
nvidia-cuda-nvrtc-cu12==12.8.93
|
||||
nvidia-cuda-runtime-cu12==12.8.90
|
||||
nvidia-cudnn-cu12==9.19.0.56
|
||||
nvidia-cufft-cu12==11.3.3.83
|
||||
nvidia-cufile-cu12==1.13.1.3
|
||||
nvidia-curand-cu12==10.3.9.90
|
||||
nvidia-cusolver-cu12==11.7.3.90
|
||||
nvidia-cusparse-cu12==12.5.8.93
|
||||
nvidia-cusparselt-cu12==0.7.1
|
||||
nvidia-nccl-cu12==2.28.9
|
||||
nvidia-nvjitlink-cu12==12.8.93
|
||||
nvidia-nvshmem-cu12==3.4.5
|
||||
nvidia-nvtx-cu12==12.8.90
|
||||
omegaconf==2.3.1
|
||||
onnxruntime==1.27.0
|
||||
openai-whisper==20250625
|
||||
optree==0.19.1
|
||||
orjson==3.11.9
|
||||
oss2==2.19.1
|
||||
packaging @ file:///home/conda/feedstock_root/build_artifacts/bld/rattler-build_packaging_1777103621/work
|
||||
pandas==3.0.3
|
||||
peft==0.19.1
|
||||
phonemizer==3.3.0
|
||||
pillow==12.2.0
|
||||
platformdirs==4.10.0
|
||||
pooch==1.9.0
|
||||
praat-parselmouth==0.4.7
|
||||
proces==0.1.7
|
||||
propcache==0.5.2
|
||||
protobuf==7.35.1
|
||||
psutil==7.2.2
|
||||
punctuators==0.0.7
|
||||
pyarrow==24.0.0
|
||||
pycparser==3.0
|
||||
pycryptodome==3.23.0
|
||||
pydantic==2.13.4
|
||||
pydantic-settings==2.14.2
|
||||
pydantic_core==2.46.4
|
||||
pydub==0.25.1
|
||||
Pygments==2.20.0
|
||||
pynndescent==0.6.0
|
||||
PyOpenGL==3.1.10
|
||||
pyparsing==3.3.2
|
||||
pyphen==0.17.2
|
||||
pypinyin==0.55.0
|
||||
python-dateutil==2.9.0.post0
|
||||
python-dotenv==1.2.2
|
||||
pyworld==0.3.5
|
||||
PyYAML==6.0.3
|
||||
rdflib==7.6.0
|
||||
referencing==0.37.0
|
||||
regex==2026.5.9
|
||||
requests==2.34.2
|
||||
rfc3986==1.5.0
|
||||
rich==15.0.0
|
||||
rpds-py==2026.5.1
|
||||
ruamel.yaml==0.18.17
|
||||
ruamel.yaml.clib==0.2.15
|
||||
safetensors==0.8.0
|
||||
scikit-learn==1.9.0
|
||||
scipy==1.18.0
|
||||
segments==2.4.0
|
||||
sentencepiece==0.2.1
|
||||
sentry-sdk==2.63.0
|
||||
setuptools==70.2.0
|
||||
shellingham==1.5.4
|
||||
simpleeval==1.0.7
|
||||
six==1.17.0
|
||||
smmap==5.0.3
|
||||
sounddevice==0.5.5
|
||||
soundfile==0.14.0
|
||||
soxr==1.1.0
|
||||
spandrel==0.4.2
|
||||
SQLAlchemy==2.0.51
|
||||
sympy==1.14.0
|
||||
tensorboardX==2.6.5
|
||||
termcolor==3.3.0
|
||||
textstat==0.7.13
|
||||
threadpoolctl==3.6.0
|
||||
tiktoken==0.13.0
|
||||
tokenizers==0.22.2
|
||||
torch==2.11.0+cu128
|
||||
torch-complex==0.4.4
|
||||
torch-einops-utils==0.1.4
|
||||
torchaudio==2.11.0+cu128
|
||||
torchcodec==0.14.0
|
||||
torchdiffeq==0.2.5
|
||||
torchfcpe==0.0.4
|
||||
torchsde==0.2.6
|
||||
torchvision==0.26.0+cu128
|
||||
tqdm==4.68.3
|
||||
trampoline==0.1.2
|
||||
transformers==5.12.1
|
||||
triton==3.6.0
|
||||
typeguard==4.5.2
|
||||
typer==0.25.1
|
||||
typing-inspection==0.4.2
|
||||
typing_extensions==4.15.0
|
||||
umap-learn==0.5.12
|
||||
Unidecode==1.4.0
|
||||
uritemplate==4.2.0
|
||||
urllib3==2.7.0
|
||||
vocos==0.1.0
|
||||
wandb==0.28.0
|
||||
webdataset==1.0.2
|
||||
wheel==0.47.0
|
||||
x-transformers==2.23.1
|
||||
xxhash==3.7.1
|
||||
yarl==1.24.2
|
||||
Reference in New Issue
Block a user