spectrogram image to wav

[ahmeftah]

Dear Authors and readers

I would appreciate it if you would give me an answer to my question:

Is it possible to convert the spectrogram image (not the array) to wav (reconstruct the wav audio from the spectrogram in image form)?

[Nadia Zueva]

hi! Yes, it is possible, vocoder (hifigan) is stored in this repo and synthesize.py calls it. Don't forget to unzip hifigan/generator_LJSpeech.pth.tar.zip (or different, depends on what ckpt you want to use) before the inference and create all necessary folders (you can check what you need to mkdir from inference errors haha)

[ahmeftah]

Thanks nestyme