It takes a long time to generate all of the samples, so you can use the pre-generated files in data/random_TTS_mp3s/. These files are great for not-wakeword samples. So if you are incrementally ...
Using the TTS generator, we will generate speech from text with the finetuned models (SGS and BAS in our case). The synthesized speech for each fine-tuned model is stored within a folder with the name ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results