speecht5_finetuned_nl_pet

This model is a fine-tuned version of microsoft/speecht5_tts on the HeinrichWirth/example dataset. It achieves the following results on the evaluation set:

• Loss: 0.4598

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• training_steps: 4000

Training results

Training Loss	Epoch	Step	Validation Loss
0.6583	1.08	250	0.5768
0.5507	2.15	500	0.5026
0.5254	3.23	750	0.4884
0.5199	4.3	1000	0.4806
0.51	5.38	1250	0.4743
0.5049	6.46	1500	0.4718
0.5001	7.53	1750	0.4686
0.5013	8.61	2000	0.4659
0.5003	9.68	2250	0.4653
0.5034	10.76	2500	0.4634
0.4922	11.83	2750	0.4633
0.4938	12.91	3000	0.4626
0.4905	13.99	3250	0.4605
0.489	15.06	3500	0.4624
0.4909	16.14	3750	0.4607
0.4904	17.21	4000	0.4598

Framework versions

• Transformers 4.32.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.4
• Tokenizers 0.13.3