trouble building then running deepmorse-decoder

[csylvain]

1. i did python -m venv deepmorse-decoder ; cd deepmorse-decoder ; git clone https://github.com/ag1le/deepmorse-decoder.git ; . ./bin/activate
2. i am not sure why 'pip install -r requirements.txt' throws an error. instead, i did pip install $(cut -d '=' -f 1 < requirements.txt)
3. the pip package 'sklearn' has been deprecated in favor of 'scikit-learn' which is already in requirements.txt ; i removed 'sklearn' from requirements.txt
4. the following dependencies are necessary (but not listed):
   a. apt install libsndfile1-dev libportmidi-dev liblo-dev libwxgtk3.2-dev libgtk-3-dev python3-pycuda
5. additional tensorflow packages are needed python3 -m pip install 'tensorflow[and-cuda]'
   a. confirm with python3 -c "import tensorflow as tf; print(tf.config.list_physical_devices('GPU'))"
6. numpy has "nan" and "inf" but not "NaN" and "Inf" - edits made in morse/MorseDecoder.py
7. after all of the above, running the system produces

$ python specgram.py
2026-01-07 19:56:16.841483: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
2026-01-07 19:56:17.326522: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: AVX2 AVX_VNNI FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.
2026-01-07 19:56:18.803633: I tensorflow/core/util/port.cc:153] oneDNN custom operations are on. You may see slightly different numerical results due to floating-point round-off errors from different computation orders. To turn them off, set the environment variable `TF_ENABLE_ONEDNN_OPTS=0`.
/home/csylvain/deepmorse-decoder/lib/python3.12/site-packages/keras/src/export/tf2onnx_lib.py:8: FutureWarning: In the future `np.object` will be defined as the corresponding NumPy scalar.
  if not hasattr(np, "object"):
Traceback (most recent call last):
  File "/home/csylvain/deepmorse-decoder/specgram.py", line 240, in <module>
    main()
  File "/home/csylvain/deepmorse-decoder/specgram.py", line 181, in main
    config = Config("model_arrl3.yaml")
             ^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/csylvain/deepmorse-decoder/morse/MorseDecoder.py", line 39, in __init__
    self.config = yaml.load(f.read())
                  ^^^^^^^^^^^^^^^^^^^
TypeError: load() missing 1 required positional argument: 'Loader'

is the information at https://stackoverflow.com/questions/75593629/how-to-load-a-tensorflow-yaml-config-file-now-that-model-from-yaml-is-depricate relevant to loading the TensorFlow model?

ps: have you seen the work at https://github.com/MaorAssayag/morse-deep-learning-detect-and-decode ? esp. the RCNN model? could that be incorporated into deepmorse-decoder ?