Using pre-trained Spear-TTS weights + Training with LibriTTS

[EomSooHwan]

I believe that whisperspeech uses Spear-TTS.

I want to use the pre-trained weights from the above huggingface link, but I don't know how exactly.

The config keys for t2s models are as follows
["depth", "n_head", "head_width", "ffn_mult", "stoks_width", "ttoks_width", "ttoks_len", "stoks_len", "ttoks_codes", "stoks_codes"]

However, I find the variables for TextToSemantic are slightly different, which makes it confusing if it is okay to use them.

Also, I want to train VoiceBox using the LibriTTS dataset, but I am struggling with setting up the training code.

For example, I wonder if there are any codes that I can refer to for training loop or dataloader coding.

Can anybody help me with these issues?