I cloned, built and ran ./lpcnet_demo without a problem. However, the command python3 training_tf2/train_lpcnet.py train_test.f32 train_test.s16 train_test --retrain ./models/lpcnet56Dcq_384_01.h5 (where lpcnet56Dcq_384_01.h5 was extracted from lpcnet_data-97e64b3.tar.gz at https://media.xiph.org/lpcnet/data/) produced the following trace:
Traceback (most recent call last):
File "/home/ksadov/LPCNet/training_tf2/train_lpcnet.py", line 188, in <module>
model.load_weights(args.retrain)
File "/home/ksadov/miniconda3/envs/lpcnet/lib/python3.10/site-packages/keras/utils/traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "<__array_function__ internals>", line 180, in transpose
File "/home/ksadov/miniconda3/envs/lpcnet/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 660, in transpose
return _wrapfunc(a, 'transpose', axes)
File "/home/ksadov/miniconda3/envs/lpcnet/lib/python3.10/site-packages/numpy/core/fromnumeric.py", line 57, in _wrapfunc
return bound(*args, **kwds)
ValueError: axes don't match array
Is this expected behavior from this file? If so, where can I obtain a pretrained checkpoint that I can resume training from?
I cloned, built and ran ./lpcnet_demo without a problem. However, the command
python3 training_tf2/train_lpcnet.py train_test.f32 train_test.s16 train_test --retrain ./models/lpcnet56Dcq_384_01.h5
(wherelpcnet56Dcq_384_01.h5
was extracted fromlpcnet_data-97e64b3.tar.gz
at https://media.xiph.org/lpcnet/data/) produced the following trace:Is this expected behavior from this file? If so, where can I obtain a pretrained checkpoint that I can resume training from?