DeepSpeech: Not found: Op type not registered 'AudioSpectrogram' in binary running on deep

Hi to all,

SYSTEM:

1. Linux deep 4.15.0-47-generic #50-Ubuntu SMP Wed Mar 13 10:44:52 UTC 2019 x86_64 x86_64 x86_64 GNU/Linux 2)Ubuntu 18.04.2 LTS

2. Python 3.6.7

3. TensorFlow: 1.13.1

4. deepspeech --version TensorFlow: v1.12.0-10-ge232881 ((((??? why not match???))) DeepSpeech: v0.4.1-0-g0e40db6

from italian dataset i have generated a pb >> pbmm but when i load the model i have this error:

(deepspeech-venv) root@deep:/home/DeepSpeech/models# deepspeech --model output_graph.pbmm --audio test.wav --alphabet alphabet.txt

Loading model from file output_graph.pbmm
TensorFlow: v1.12.0-10-ge232881
DeepSpeech: v0.4.1-0-g0e40db6
Warning: reading entire model file into memory. Transform model file into an mmapped graph to reduce heap usage.
2019-04-29 10:31:23.380831: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
Not found: Op type not registered 'AudioSpectrogram' in binary running on deep. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) `tf.contrib.resampler` should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.
Traceback (most recent call last):
  File "/root/tmp/deepspeech-venv/bin/deepspeech", line 10, in <module>
    sys.exit(main())
  File "/root/tmp/deepspeech-venv/lib/python3.6/site-packages/deepspeech/client.py", line 80, in main
    ds = Model(args.model, N_FEATURES, N_CONTEXT, args.alphabet, BEAM_WIDTH)
  File "/root/tmp/deepspeech-venv/lib/python3.6/site-packages/deepspeech/__init__.py", line 14, in __init__
    raise RuntimeError("CreateModel failed with error code {}".format(status))
RuntimeError: CreateModel failed with error code 5

Not found: Op type not registered 'AudioSpectrogram' in binary running on deep. Make sure the Op and Kernel are registered in the binary running in this process. Note that if you are loading a saved graph which used ops from tf.contrib, accessing (e.g.) tf.contrib.resampler should be done before importing the graph, as contrib ops are lazily registered when the module is first accessed.