speecht5_Kobe_finetune

This model is a fine-tuned version of blackbook-lab/speecht5_Kobe_finetune on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6849

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: 8
• eval_batch_size: 2
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8442	0.3704	10	0.7189
0.7748	0.7407	20	0.7182
0.7356	1.1111	30	0.7198
0.8104	1.4815	40	0.7147
1.5772	1.8519	50	0.7209
0.6864	2.2222	60	0.7140
0.9694	2.5926	70	0.7117
0.7178	2.9630	80	0.7107
0.6012	3.3333	90	0.7027
0.6419	3.7037	100	0.6981
0.8538	4.0741	110	0.6981
0.7592	4.4444	120	0.6877
0.6722	4.8148	130	0.6849

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1