I want to test pretrained model.
so I did it like manual in mozila deep speech github.
deepspeech --model model/output_graph.pbmm --alphabet model/alphabet.txt --lm model/lm.binary --trie model/trie --audio model/test.wav
output is just below.
Loaded model in 0.583s.
Loading language model from files model/lm.binary model/trie
Loaded language model in 25.0s.
2019-07-08 06:41:37.001199: I tensorflow/stream_executor/dso_loader.cc:152] successfully opened CUDA library libcublas.so.10.0 locally
juries commencing writing in the whiplike
Inference took 1.447s for 4.584s audio file.
I want to know the encoded text.
How can I find it?