SpeechT5-fine-tune-en

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

• Loss: 0.4473

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: 0.0001
• 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
4.6694	0.3583	100	0.5087
4.3795	0.7165	200	0.4933
4.1725	1.0748	300	0.4727
4.061	1.4330	400	0.4695
3.9896	1.7913	500	0.4633
3.941	2.1496	600	0.4580
3.8944	2.5078	700	0.4538
3.8968	2.8661	800	0.4522
3.79	3.2244	900	0.4499
3.8059	3.5826	1000	0.4473

Framework versions

• Transformers 4.46.0.dev0
• Pytorch 2.4.1+cu121
• Datasets 3.0.2
• Tokenizers 0.20.1