Byte-parity with pyannote-PyTorch reference (cosine 0.763718 identical at 6 decimals on 200 cross-window slot pairs). 2.5x faster than pyannote-MPS on Apple Silicon native. Extracted from gitea.tavportal.com/olivier/MLX_CONVERTOR commit 5f9eafa.
19 lines
150 B
Plaintext
19 lines
150 B
Plaintext
__pycache__/
|
|
*.py[cod]
|
|
*.class
|
|
*.so
|
|
.Python
|
|
.venv/
|
|
venv/
|
|
ENV/
|
|
dist/
|
|
build/
|
|
*.egg-info/
|
|
.eggs/
|
|
.DS_Store
|
|
.env
|
|
*.log
|
|
.pytest_cache/
|
|
.ruff_cache/
|
|
*.orig
|