speecht5_finetunedml

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: 0.5376

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 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
0.805	0.1161	100	0.6954
0.6797	0.2323	200	0.5990
0.6391	0.3484	300	0.5751
0.6305	0.4646	400	0.5646
0.618	0.5807	500	0.5551
0.6137	0.6969	600	0.5485
0.5983	0.8130	700	0.5438
0.6	0.9292	800	0.5410
0.5935	1.0453	900	0.5384
0.5954	1.1614	1000	0.5376

Framework versions

• Transformers 4.47.0
• Pytorch 2.5.1+cu121
• Datasets 3.3.1
• Tokenizers 0.21.0