I'm trying to use this code but with a customer dataset. My wanted word is only one word which is a different case than the original code. In the dataset folder, I have two folders, one is the wanted word, and the other has random sounds.
When running the code on your dataset it works fine. However, when using my dataset I'm getting the following error
[
`Traceback (most recent call last):
File "test.py", line 221, in
test()
File "test.py", line 53, in test
model = train.train(FLAGS)
File "C:\Users\XXX\tflu-kws-cortex-m3\Training\train.py", line 86, in train
callbacks=[model_checkpoint_callback, tensorboard_callback])
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\keras\engine\training.py", line 1184, in fit
tmp_logs = self.train_function(iterator)
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\def_function.py", line 885, in call
result = self._call(*args, **kwds)
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\def_function.py", line 917, in _call
return self._stateless_fn(*args, **kwds) # pylint: disable=not-callable
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\function.py", line 3040, in call
filtered_flat_args, captured_inputs=graph_function.captured_inputs) # pylint: disable=protected-access
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\function.py", line 1964, in _call_flat
ctx, args, cancellation_manager=cancellation_manager))
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\function.py", line 596, in call
ctx=ctx)
File "C:\Users\XXX\anaconda3\envs\yamnet\lib\site-packages\tensorflow\python\eager\execute.py", line 60, in quick_execute
inputs, attrs, num_outputs)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Data too short when trying to read string
[[{{node DecodeWav}}]]
[[IteratorGetNext]] [Op:__inference_train_function_9995]
Function call stack:
train_function](url) `](url)
ARM-software
