I have ran CPU inference for 1 min audio and it took around 20 sec.
By that logic 30 min audio should take 10 min…
I am running inference for 30 min file for over an hour now - the CPU load is 50% and there are no errors and it still running.
Any suggestions?
deepspeech --model models/output_graph.pbmm --alphabet models/alphabet.txt --lm models/lm.binary --trie models/trie --audio 30m.wav
Loading model from file models/output_graph.pbmm
TensorFlow: v1.13.1-10-g3e0cc53
DeepSpeech: v0.5.1-0-g4b29b78
2019-10-14 19:08:31.699341: I tensorflow/core/platform/cpu_feature_guard.cc:141] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2 AVX512F FMA
2019-10-14 19:08:31.738316: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "UnwrapDatasetVariant" device_type: "CPU"') for unknown op: UnwrapDatasetVariant
2019-10-14 19:08:31.738390: 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
2019-10-14 19:08:31.738406: E tensorflow/core/framework/op_kernel.cc:1325] OpKernel ('op: "WrapDatasetVariant" device_type: "CPU"') for unknown op: WrapDatasetVariant
2019-10-14 19:08:31.738544: 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
Loaded model in 0.13s.
Loading language model from files models/lm.binary models/trie
Loaded language model in 23.2s.
Warning: original sample rate (48000) is different than 16kHz. Resampling might produce erratic speech recognition.
Running inference.