speecht5_tts_id_audiobook-tts

This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4371

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 1e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.5678	1.6447	500	0.4930
0.5163	3.2895	1000	0.4662
0.474	4.9342	1500	0.4508
0.4806	6.5789	2000	0.4460
0.4689	8.2237	2500	0.4410
0.4759	9.8684	3000	0.4377
0.4676	11.5132	3500	0.4358
0.4751	13.1579	4000	0.4371

Framework versions

• Transformers 4.56.2
• Pytorch 2.8.0+cu129
• Datasets 3.6.0
• Tokenizers 0.22.1