speecht5_finetuned_commonvoice_polish_1000_10k

This model is a fine-tuned version of Dawid511/speecht5_finetuned_commonvoice_polish_500_10k on the common_voice_17_0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.4561

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: 8
• total_train_batch_size: 32
• 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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5301	0.3431	100	0.4937
0.5276	0.6861	200	0.4910
0.5209	1.0292	300	0.4826
0.5084	1.3722	400	0.4772
0.5086	1.7153	500	0.4763
0.5056	2.0583	600	0.4681
0.4981	2.4014	700	0.4655
0.4924	2.7444	800	0.4611
0.4861	3.0875	900	0.4618
0.4833	3.4305	1000	0.4561

Framework versions

• Transformers 4.46.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3