speecht5_finetuned_English_Technical_Shabdobhedii

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: 0.4481

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: 1000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5889	0.3581	100	0.5117
0.5419	0.7162	200	0.4928
0.5203	1.0743	300	0.4762
0.5079	1.4324	400	0.4699
0.5022	1.7905	500	0.4580
0.4952	2.1486	600	0.4601
0.4886	2.5067	700	0.4579
0.4853	2.8648	800	0.4520
0.4762	3.2229	900	0.4477
0.4774	3.5810	1000	0.4481

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.2
• Tokenizers 0.19.1