speecht5_finetuned_voxpopuli_hr

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

• Loss: 0.5769

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: 1
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 8
• optimizer: Use adamw_torch 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: 5
• training_steps: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7244	0.0119	10	0.6521
0.6997	0.0239	20	0.6255
0.5865	0.0358	30	0.6029
0.593	0.0478	40	0.5946
0.6074	0.0597	50	0.5896
0.5793	0.0717	60	0.5830
0.5679	0.0836	70	0.5806
0.5869	0.0955	80	0.5793
0.5647	0.1075	90	0.5777
0.5902	0.1194	100	0.5769

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0