speecht5_finetuned_krio

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4377

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: 12
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 48
• 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: 800
• training_steps: 12000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4893	14.9323	1000	0.4632
0.4704	29.8571	2000	0.4480
0.4623	44.7820	3000	0.4417
0.4545	59.7068	4000	0.4386
0.4491	74.6316	5000	0.4380
0.448	89.5564	6000	0.4364
0.4445	104.4812	7000	0.4352
0.4425	119.4060	8000	0.4355
0.4443	134.3308	9000	0.4355
0.4411	149.2556	10000	0.4366
0.439	164.1805	11000	0.4360
0.4425	179.1053	12000	0.4377

Framework versions

• Transformers 4.57.2
• Pytorch 2.9.0+cu126
• Datasets 4.4.1
• Tokenizers 0.22.1