speecht5_finetuned_librispeech_polish_epo10_batch4_gas2

This model is a fine-tuned version of dawid511/speecht5_finetuned_librispeech_polish_epo10_batch2_gas4 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3666

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 2
• 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: 300
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.7579	1.5320	300	0.3742
0.7303	3.0614	600	0.3737
0.748	4.5934	900	0.3832
0.7232	6.1228	1200	0.3680
0.7221	7.6547	1500	0.3661
0.712	9.1841	1800	0.3666

Framework versions

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