speecht5_finetuned_id

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: 0.4136

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: 1e-05
• 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: 500
• training_steps: 10000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5008	0.3417	1000	0.4541
0.4648	0.6834	2000	0.4365
0.4547	1.0249	3000	0.4288
0.4555	1.3666	4000	0.4235
0.4474	1.7084	5000	0.4195
0.4459	2.0499	6000	0.4182
0.4438	2.3916	7000	0.4157
0.4511	2.7333	8000	0.4148
0.441	3.0748	9000	0.4132
0.4431	3.4165	10000	0.4136

Framework versions

• Transformers 4.51.3
• Pytorch 2.5.1+cu121
• Datasets 3.5.1
• Tokenizers 0.21.1