This is an environment for training a Korean speech synthesis model.
981
final tag : VAE Tacotron2, HiFi-GAN, VITS, VITS2, RVC-VITS2, P-Flow training enviroment using AIHUB Datasets.
Content type
Image
Digest
sha256:75cff68b8…
Size
25.8 GB
Last updated
almost 2 years ago
docker pull 0913ktg/tts_image:RVCv2