Replies: 1 comment
-
>>> lissyx |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
>>> rajpuneet.sandhu
[August 23, 2019, 6:46pm]
I am getting the following error after training is finished and the
model is to exported. I used slash --export_tflite and slash --nouse_seq_length
options:
> Traceback (most recent call last): slash
> File 'DeepSpeech.py', line 837, in slash
> tf.app.run(main) slash
> File
> '/data/DeepSpeech/venv/lib/python3.6/site-packages/tensorflow/python/platform/app.py',
> line 125, in run slash
> slash _sys.exit(main(argv)) slash
> File 'DeepSpeech.py', line 829, in main slash
> export() slash
> File 'DeepSpeech.py', line 681, in export slash
> inputs, outputs, slash _ =
> create_inference_graph(batch_size=FLAGS.export_batch_size,
> n_steps=FLAGS.n_steps, tflite=FLAGS.export_tflite) slash
> File 'DeepSpeech.py', line 596, in create_inference_graph slash
> seq_length=seq_length if FLAGS.use_seq_length else None, slash
> File
> '/data/DeepSpeech/venv/lib/python3.6/site-packages/tensorflow/python/platform/flags.py',
> line 85, in getattr slash
> return wrapped.getattr(name) slash
> File
> '/data/DeepSpeech/venv/lib/python3.6/site-packages/absl/flags/ slash _flagvalues.py',
> line 473, in getattr slash
> raise AttributeError(name) slash
> AttributeError: use_seq_length
[This is an archived TTS discussion thread from discourse.mozilla.org/t/unable-to-export-tflite-model]
Beta Was this translation helpful? Give feedback.
All reactions