speecht5_finetuned_librispeech_polish_epo3_batch2_gas4

This model is a fine-tuned version of dawid511/speecht5_finetuned_librispeech_polish_epo3_batch2_gas2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3694

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: 4
• 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: 100
• training_steps: 700
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.6881	0.5115	100	0.4005
1.6295	1.0205	200	0.3932
1.6458	1.5320	300	0.3826
1.5841	2.0409	400	0.3786
1.5994	2.5524	500	0.3770
1.5545	3.0614	600	0.3718
1.5633	3.5729	700	0.3694

Framework versions

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