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.

つくよみちゃんコーパスを用いたStyleBertVITS2の事前学習データ

学習パラメータ

バッチサイズは、途中で8 → 12に変更 epochsは学習が終わった後に随時追加をして、追加学習をしています。

"train": {
    "log_interval": 200,
    "eval_interval": 5000,
    "seed": 42,
    "epochs": 2000,
    "learning_rate": 0.0001,
    "betas": [
      0.8,
      0.99
    ],
    "eps": 1e-09,
    "batch_size": 12,
    "bf16_run": true,
    "fp16_run": false,
    "lr_decay": 0.99996,
    "segment_size": 16384,
    "init_lr_ratio": 1,
    "warmup_epochs": 0,
    "c_mel": 45,
    "c_kl": 1.0,
    "c_commit": 100,
    "skip_optimizer": true,
    "freeze_ZH_bert": false,
    "freeze_JP_bert": false,
    "freeze_EN_bert": false,
    "freeze_emo": false,
    "freeze_style": false
  }

学習リソーる

  • NVIDIA-L4
  • ubuntu22.04

sppech mosによる定量評価

Downloads last month
2
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support