speecht5_finetuned_voice_dataset_bn_v_4

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: 0.5560

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: 125
• training_steps: 3000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6302	12.1212	250	0.5979
0.5895	24.2424	500	0.5645
0.5658	36.3636	750	0.5638
0.5495	48.4848	1000	0.5609
0.5541	60.6061	1250	0.5443
0.5431	72.7273	1500	0.5522
0.5321	84.8485	1750	0.5406
0.5321	96.9697	2000	0.5515
0.5267	109.0909	2250	0.5674
0.5334	121.2121	2500	0.5607
0.5202	133.3333	2750	0.5586
0.52	145.4545	3000	0.5560

Framework versions

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