Prepare .wav or .amr files for yamnet.tflite model Android
After a lot of research, I realized there is no any easiest way to prepare a local .wav or .amr file for yamnet.tflite model, as we know that any AI model takes a specific type or shape as an input, but the question is, What if the input file did not meet the model input requirements?
In this article, I will explain to you how to prepare local .wav or .amr files for yamnet.tflite model.
Yamnet model input:
The model accepts a 1-D float32
Tensor or NumPy array of length 15600 containing a 0.975-second waveform represented as mono 16 kHz samples in the range [-1.0, +1.0]
. read more…
Step-1
Add these dependencies to the app-level build.gradle file
Step-2
Prepare input file and run the model
Finally, the output contains the model results
Happy coding…