speecht5_finetuned_librispeech_polish_epo20_batch4_gas4

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

• Loss: 0.3620

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: 4
• total_train_batch_size: 16
• 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: 200
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
1.812	2.0409	200	0.4076
1.6866	4.0818	400	0.3869
1.6252	6.1228	600	0.3790
1.6036	8.1637	800	0.3747
1.5387	10.2046	1000	0.3672
1.5533	12.2455	1200	0.3672
1.5278	14.2864	1400	0.3646
1.4964	16.3274	1600	0.3634
1.4883	18.3683	1800	0.3620

Framework versions

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