speecht5_mehdi_new_as_try

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: 0.4777

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
0.6299	1.7778	100	0.5641
0.5678	3.5556	200	0.5297
0.5517	5.3333	300	0.5078
0.5409	7.1111	400	0.5074
0.5228	8.8889	500	0.4911
0.517	10.6667	600	0.4862
0.5058	12.4444	700	0.4817
0.4967	14.2222	800	0.4779
0.49	16.0	900	0.4777
0.4908	17.7778	1000	0.4777

Framework versions

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