speecht5_finetuned_essam3_ar

This model is a fine-tuned version of MBZUAI/speecht5_tts_clartts_ar on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3401

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: 0.0001
• train_batch_size: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use adamw_torch 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: 100
• training_steps: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.3793	0.3742	100	0.3576
0.3909	0.7484	200	0.3589
0.3873	1.1225	300	0.3526
0.3819	1.4967	400	0.3529
0.3777	1.8709	500	0.3534
0.3776	2.2451	600	0.3520
0.376	2.6193	700	0.3460
0.368	2.9935	800	0.3445
0.3658	3.3676	900	0.3417
0.3642	3.7418	1000	0.3401

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3