uz_2301_3.1_tts

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: 0.4577

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: 0.0003
• train_batch_size: 32
• eval_batch_size: 16
• seed: 42
• optimizer: Use adamw_bnb_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 7000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5566	10.0	500	0.4779
0.441	20.0	1000	0.4353
0.4194	30.0	1500	0.4364
0.4018	40.0	2000	0.4254
0.3771	50.0	2500	0.4184
0.3807	60.0	3000	0.4363
0.3615	70.0	3500	0.4384
0.3492	80.0	4000	0.4462
0.3323	90.0	4500	0.4423
0.3281	100.0	5000	0.4445
0.3299	110.0	5500	0.4454
0.3145	120.0	6000	0.4464
0.3192	130.0	6500	0.4540
0.3108	140.0	7000	0.4577

Framework versions

• Transformers 4.48.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.21.0