1# lpcnet-testsuite 2 3## setup 4The test script is written for Linux only. It requires sox to be installed and available. 5 6Setup is done as usual via 7 8``` 9pip install -r requirements.txt 10``` 11 12The test scrip run_warpq_test.py requires a setup file in yaml format, which specifies how 13to generate a wave file OUTPUT from a wave file INPUT sampled resampled to the specified 14sampling rate as a list of shell commands. This makes it easy to test other neural vocoders 15with it as well. Two examples are given in examples. INPUT and OUTPUT will be replaced by using 16the string.format(INPUT=input,OUTPUT=output) method. 17 18Here is one example: 19 20``` 21test: "LPCNet reference test" 22processing: 23 - "sox {INPUT} {INPUT}.raw" 24 - "/local/code/LPCNet/lpcnet_demo -features {INPUT}.raw {INPUT}.features.f32" 25 - "/local/code/LPCNet/lpcnet_demo -synthesis {INPUT}.features.f32 {INPUT}.decoded.raw" 26 - "sox -r 16000 -L -e signed-integer -b 16 -c 1 {INPUT}.decoded.raw {OUTPUT}" 27``` 28 29The structure of the output folder is as follows: 30 31``` 32output_folder 33+-- html 34 +-- index.html 35 +-- items 36+-- processing 37+-- setup.yml 38+-- stats.txt 39+-- scores.txt 40``` 41 42scores.txt contains the WARP-Q scores in descending order (best to worse) 43stats.txt contains mean values over all, the 10 best and the 10 worst items 44setup.yml contains all information to repeat the run 45htms contains a self-contained website displaying the 10 best and 10 worst items 46processing contains processing output