Open fducau opened 1 year ago
I found a combination of packages that seems to be working well:
python = "^3.10"
torch = "1.12.0"
torchaudio = "0.12.0"
pytorch-lightning = "1.9.0"
torchaudio-augmentations = "0.2.4"
simclr = "1.0.2"
torch-pitch-shift = "1.2.4"
soundfile = "^0.12.1"
matplotlib = "^3.7.1"
scikit-learn = "^1.2.2"
All tests passing:
> ~/clmr$ poetry run pytest
============================================================================ test session starts =============================================================================
platform linux -- Python 3.10.6, pytest-7.3.1, pluggy-1.0.0
rootdir: /my-repos-path/clmr
collected 4 items
tests/test_audioset.py . [ 25%]
tests/test_dataset.py .. [ 75%]
tests/test_spectogram.py . [100%]
============================================================================= 4 passed in 4.05s ==============================================================================
I want to implement the CLMR model for genre detection on GTZAN dataset and and then try to tweak the architecture a bit maybe. Can someone please help?
Hi! It seems there is some dependency issue going on. I've been troubleshooting locally with no luck.
When running the installation bit of the colab notebook I'm getting the following:
Currently investigating a good dependency configuration for this repo. Info welcome.