speecht5_finetuned_own_polish_epo6_batch2_gas3

This model is a fine-tuned version of dawid511/speecht5_finetuned_own_polish_epo3_batch2_gas3 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3702

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: 0.0001
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 3
• total_train_batch_size: 6
• 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: 100
• num_epochs: 6
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.1996	0.6	100	0.3914
1.2201	1.204	200	0.3986
1.1801	1.804	300	0.3914
1.1896	2.408	400	0.3835
1.2196	3.012	500	0.3777
1.2003	3.612	600	0.3876
1.1593	4.216	700	0.3748
1.1472	4.816	800	0.3759
1.1427	5.42	900	0.3702

Framework versions

• Transformers 4.47.1
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0