speecht5_finetuned_sudhanshu_hi

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: 0.4082

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 OptimizerNames.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: 1500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5315	0.6457	100	0.4919
0.5054	1.2906	200	0.4711
0.4983	1.9362	300	0.4706
0.4946	2.5811	400	0.4567
0.4847	3.2260	500	0.4469
0.486	3.8717	600	0.4322
0.4782	4.5165	700	0.4320
0.4626	5.1614	800	0.4309
0.4532	5.8071	900	0.4229
0.4477	6.4520	1000	0.4190
0.4426	7.0969	1100	0.4187
0.4437	7.7425	1200	0.4140
0.4384	8.3874	1300	0.4115
0.4366	9.0323	1400	0.4125
0.4415	9.6780	1500	0.4082

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1