Hi!
I’m working with my own speech2text project and when I found DeepSpeech project, I was very happy. However, when I tried applying prediction for the default data, I got result like this
deepspeech --model ./models/output_graph.pbmm --audio ./audio/2830-3980-0043.wav --alphabet ./models/alphabet.txt
Loading model from file ./models/output_graph.pbmm
TensorFlow: v1.13.1-10-g3e0cc5374d
DeepSpeech: v0.5.1-0-g4b29b78
2019-07-22 16:58:20.656064: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 FMA
2019-07-22 16:58:20.663496: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel (‘op: “UnwrapDatasetVariant” device_type: “GPU” host_memory_arg: “input_handle” host_memory_arg: “output_handle”’) for unknown op: UnwrapDatasetVariant
2019-07-22 16:58:20.663534: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel (‘op: “UnwrapDatasetVariant” device_type: “CPU”’) for unknown op: UnwrapDatasetVariant
2019-07-22 16:58:20.663545: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel (‘op: “WrapDatasetVariant” device_type: “GPU” host_memory_arg: “input_handle” host_memory_arg: “output_handle”’) for unknown op: WrapDatasetVariant
2019-07-22 16:58:20.663554: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel (‘op: “WrapDatasetVariant” device_type: “CPU”’) for unknown op: WrapDatasetVariant
Loaded model in 0.0102s.
Running inference.
experienced proof this
Inference took 1.760s for 1.975s audio file.
It appears to work, but I couldn’t receive any result. Where did I go wrong?
My version setting was:
- DeepSpeech module: deepspeech-0.5.1-cp36-cp36m-macosx_10_10_x86_64.whl
- Model: deepspeech-0.5.1-models.tar.gz
- Test audio: audio-0.5.1.tar.gz
Thanks in advance.