readme and deps

README.md

@@ -0,0 +1,36 @@
+# Description
+
+This project started as an attempt to run diarization on mac.
+As a demo data, I used:
+
+yt-dlp https://vod.tvp.pl/programy,88/jeden-z-dziesieciu-odcinki,274174/odcinek-3492,S01E3492,2138001
+
+Rename to: jeden-z-10-final.mp4
+
+and run the script:
+
+```bash
+source .venv/bin/activate
+python transcribe.py
+```
+
+
+## First time setup
+
+```bash
+git clone <your-repo>
+cd <your-repo>
+
+# create their own isolated venv (name doesn’t have to match)
+python -m venv .venv
+source .venv/bin/activate        # or .venv\Scripts\activate on Windows
+
+pip install --upgrade pip setuptools wheel
+pip install -r requirements.txt
+```
+
+make sure ffmpeg is installed and available in PATH
+
+```bash
+ffmpeg -version
+```

requirements.txt

@@ -0,0 +1,110 @@
+aiohappyeyeballs==2.6.1
+aiohttp==3.12.7
+aiosignal==1.3.2
+alembic==1.16.1
+antlr4-python3-runtime==4.9.3
+asteroid-filterbanks==0.4.0
+attrs==25.3.0
+av==14.4.0
+certifi==2025.4.26
+cffi==1.17.1
+charset-normalizer==3.4.2
+click==8.2.1
+coloredlogs==15.0.1
+colorlog==6.9.0
+contourpy==1.3.2
+ctranslate2==4.4.0
+cycler==0.12.1
+docopt==0.6.2
+dotenv==0.9.9
+einops==0.8.1
+faster-whisper==1.1.1
+filelock==3.18.0
+flatbuffers==25.2.10
+fonttools==4.58.1
+frozenlist==1.6.2
+fsspec==2025.5.1
+hf-xet==1.1.3
+huggingface-hub==0.32.4
+humanfriendly==10.0
+HyperPyYAML==1.2.2
+idna==3.10
+Jinja2==3.1.6
+joblib==1.5.1
+julius==0.2.7
+kiwisolver==1.4.8
+lightning==2.5.1.post0
+lightning-utilities==0.14.3
+llvmlite==0.44.0
+Mako==1.3.10
+markdown-it-py==3.0.0
+MarkupSafe==3.0.2
+matplotlib==3.10.3
+mdurl==0.1.2
+more-itertools==10.7.0
+mpmath==1.3.0
+multidict==6.4.4
+networkx==3.5
+nltk==3.9.1
+numba==0.61.2
+numpy==2.2.6
+omegaconf==2.3.0
+onnxruntime==1.22.0
+openai-whisper==20240930
+optuna==4.3.0
+packaging==24.2
+pandas==2.2.3
+pillow==11.2.1
+primePy==1.3
+propcache==0.3.1
+protobuf==6.31.1
+pyannote.audio==3.3.2
+pyannote.core==5.0.0
+pyannote.database==5.1.3
+pyannote.metrics==3.2.1
+pyannote.pipeline==3.0.1
+pycparser==2.22
+Pygments==2.19.1
+pyparsing==3.2.3
+python-dateutil==2.9.0.post0
+python-dotenv==1.1.0
+pytorch-lightning==2.5.1.post0
+pytorch-metric-learning==2.8.1
+pytz==2025.2
+PyYAML==6.0.2
+regex==2024.11.6
+requests==2.32.3
+rich==14.0.0
+ruamel.yaml==0.18.12
+ruamel.yaml.clib==0.2.12
+safetensors==0.5.3
+scikit-learn==1.6.1
+scipy==1.15.3
+semver==3.0.4
+sentencepiece==0.2.0
+shellingham==1.5.4
+six==1.17.0
+sortedcontainers==2.4.0
+soundfile==0.13.1
+speechbrain==1.0.3
+SQLAlchemy==2.0.41
+sympy==1.14.0
+tabulate==0.9.0
+tensorboardX==2.6.2.2
+threadpoolctl==3.6.0
+tiktoken==0.9.0
+tokenizers==0.21.1
+torch==2.7.0
+torch-audiomentations==0.12.0
+torch_pitch_shift==1.2.5
+torchaudio==2.7.0
+torchmetrics==1.7.2
+torchvision==0.22.0
+tqdm==4.67.1
+transformers==4.52.4
+typer==0.16.0
+typing_extensions==4.14.0
+tzdata==2025.2
+urllib3==2.4.0
+whisperx==3.3.4
+yarl==1.20.0