speecht5_finetuned_Kishor798

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: 0.3929

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5996	2.7586	100	0.5090
0.5137	5.5172	200	0.4987
0.4994	8.2759	300	0.4610
0.4647	11.0345	400	0.4576
0.4384	13.7931	500	0.4316
0.4215	16.5517	600	0.4129
0.419	19.3103	700	0.4168
0.3984	22.0690	800	0.4082
0.3897	24.8276	900	0.4014
0.3875	27.5862	1000	0.3985
0.3739	30.3448	1100	0.3959
0.3656	33.1034	1200	0.3991
0.3641	35.8621	1300	0.3904
0.3614	38.6207	1400	0.3901
0.3657	41.3793	1500	0.3929

Framework versions

• Transformers 4.44.2
• Pytorch 2.5.0+cu121
• Datasets 3.1.0
• Tokenizers 0.19.1