Model Summary
This model is a fine-tuned version of XTTS-v2 on a custom dataset.
Training and Evaluation Data
- Audio collected from an audiobook.
Training Hyperparameters
The following hyperparameters were used during training:
GPTArgs
max_conditioning_length = 143677min_conditioning_length = 66150max_wav_length = 255995max_text_length = 66150gpt_use_masking_gt_prompt_approach = Truegpt_use_perceiver_resampler = True
GPTTrainerConfig
BATCH_SIZE = 3batch_group_size = 48GRAD_ACUMM_STEPS = 84optimizer_params = {"betas": [0.9, 0.96], "eps": 1e-8, "weight_decay": 1e-2}lr_scheduler_params = {"milestones": [50000 * 18, 150000 * 18, 300000 * 18], "gamma": 0.5, "last_epoch": -1}
Framework Versions
- Transformers:
4.51.3
- PyTorch:
2.6.0+cu126
- TorchAudio:
2.6.0
- Tokenizers:
0.21.1
- TTS
