SaberMolaei/speecht5_tts_ckb7

SpeechT5 tts ckb7- Saber Molaei

This model is a fine-tuned version of microsoft/speecht5_tts on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

• Loss: 0.5043

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: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• 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: 7000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.6297	2.93	1000	0.5741
0.5784	5.85	2000	0.5376
0.5576	8.78	3000	0.5230
0.5563	11.7	4000	0.5120
0.5257	14.63	5000	0.5070
0.5375	17.56	6000	0.5028
0.5365	20.48	7000	0.5043

Framework versions

• Transformers 4.30.0.dev0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3