speecht5_finetuned_l2art_en

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: 0.3775

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: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.4109	1.5717	100	0.3810
0.4201	3.1434	200	0.3802
0.4138	4.7151	300	0.3797
0.4104	6.2868	400	0.3776
0.4035	7.8585	500	0.3805
0.4021	9.4303	600	0.3783
0.395	11.0020	700	0.3755
0.3997	12.5737	800	0.3771
0.3918	14.1454	900	0.3772
0.395	15.7171	1000	0.3763
0.3862	17.2888	1100	0.3771
0.397	18.8605	1200	0.3780
0.3903	20.4322	1300	0.3795
0.391	22.0039	1400	0.3780
0.3964	23.5756	1500	0.3775

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1