speecht5_finetuned_male_globo_add_token_3_commonvoice_1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3535

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4234	1.96	1000	0.3852
0.4022	3.91	2000	0.3719
0.3845	5.87	3000	0.3663
0.3838	7.83	4000	0.3620
0.3818	9.79	5000	0.3614
0.3798	11.74	6000	0.3590
0.3748	13.7	7000	0.3565
0.3734	15.66	8000	0.3549
0.3766	17.62	9000	0.3535
0.3753	19.57	10000	0.3535

Framework versions

• Transformers 4.39.0.dev0
• Pytorch 2.2.1
• Datasets 2.18.0
• Tokenizers 0.15.2