AdaCodruta/tts_rodigits

sst_rodigits

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: 0.3581

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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4289	2.8777	1000	0.3812
0.413	5.7554	2000	0.3675
0.3956	8.6331	3000	0.3624
0.3954	11.5108	4000	0.3588
0.3911	14.3885	5000	0.3581

Framework versions

• Transformers 4.40.2
• Pytorch 2.5.1+cu118
• Datasets 3.1.0
• Tokenizers 0.19.1