Lines Matching refs:model

22 MobileNet tensorflow lite model based on:
34 8bit quantized MobileNet tensorflow lite model based on:
46 MobileNet v2 tensorflow lite model based on:
58 8bit quantized MobileNet v2 tensorflow lite model based on:
70 Float version of MobileNet SSD tensorflow model based on:
83 8bit quantized MobileNet SSD tensorflow lite model based on:
96 TTS tensorflow lite model based on:
102 Note that the tensorflow lite model is the acoustic model in the paper. It is used because it is
103 much heavier than the duration model.
106 ASR tensorflow lite model based on the ASR acoustic model in:
141 TODO(pszczepaniak): Provide at least 5 inputs outputs for each model