Low Latency TensorFlow Live Speech Recognition with JACK audio daemon in Linux Ubuntu
Two C/C++ programs on top of speech_commands/test_streaming_accuracy.cc which use JACK2 audio server in Linux to capture the sound and perform real-time audio recognition with little delay(~30ms).
The source codes can be found at:
1. test_live_stream.cc :
https://github.com/Alireza89/tensorfl...
2. jack_capture_tensorflow.c :
https://github.com/Alireza89/tensorfl...
3. Updated BUILD file for Bazel :
https://github.com/Alireza89/tensorfl...