You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

StableTTSの日本語事前学習

モデルパラメータ

48M

Total parameters: 48,171,521
Trainable parameters: 48,171,521

学習時のモデルパラメータ

    hidden_channels: int = 256
    filter_channels: int = 1024
    n_heads: int = 4
    n_enc_layers: int = 8
    n_dec_layers: int = 8
    kernel_size: int = 3
    p_dropout: float = 0.1
    gin_channels: int = 256

トレーニングパラメータ

    train_dataset_path: str = 'filelists/filelist.json'
    test_dataset_path: str = 'filelists/filelist.json'
    batch_size: int = 16
    learning_rate: float = 1e-4
    num_epochs: int = 15
    model_save_path: str = './checkpoints'
    log_dir: str = './runs'
    log_interval: int = 0.01
    save_interval: int = 1
    warmup_steps: int = 0.5
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference Providers NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API: The model has no library tag.

Dataset used to train ayousanz/stable-tts-moe-speech-2