Finetuned_speecht5_2

This model is a fine-tuned version of microsoft/speecht5_tts on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4976

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: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• 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: 5000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5279	5.9172	500	0.4841
0.5081	11.8343	1000	0.4887
0.4844	17.7515	1500	0.4822
0.4897	23.6686	2000	0.4829
0.4708	29.5858	2500	0.4898
0.4801	35.5030	3000	0.4916
0.4805	41.4201	3500	0.4923
0.4617	47.3373	4000	0.5006
0.4761	53.2544	4500	0.4999
0.4616	59.1716	5000	0.4976

Framework versions

• Transformers 4.42.3
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.19.1