finetuned_speecht5_50Kdata

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3766

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5055	0.3505	500	0.4585
0.4679	0.7010	1000	0.4248
0.4444	1.0515	1500	0.4140
0.4356	1.4020	2000	0.4109
0.434	1.7525	2500	0.4082
0.428	2.1030	3000	0.4023
0.423	2.4536	3500	0.4003
0.4177	2.8041	4000	0.3835
0.4077	3.1546	4500	0.3766
0.4096	3.5051	5000	0.3781

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1