This is a brief introduction for model ckpts.
original models:
- bigvgan_discriminator.pth
- bigvgan_generator.pth
- bpe.model (tokenizer)
- config.yaml (original inference configuration)
- gpt.pth (backbone transformer)
- dvae.pth (use for getting training audio tokens)
- unigram_12000.vocab (tokenizer vocabulary)
fine-tuned models:
- Cantonese Model:
a. config_yue.yaml
b. gpt_tuned_yue.pth
c. gpt_yue.pth (useless only for start stage in training)
- Janpanese Model:
a. config_ja.yaml
b. gpt_tuned_ja.pth
c. gpt_tuned_ja_v2.pth
c. gpt_ja.pth (useless only for start stage in training)
- Malaya Model:
a. config_malay.yaml
b. gpt_malaya_tuned.pth
c. gpt_malay.pth (useless only for start stage in training)
