speecht5_female_british_english

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: 0.4238

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 100
• training_steps: 500
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.5746	0.4890	100	0.5047
0.5227	0.9780	200	0.4599
0.4868	1.4670	300	0.4509
0.4767	1.9560	400	0.4294
0.4599	2.4450	500	0.4238

Framework versions

• Transformers 4.45.1
• Pytorch 2.1.0+cu118
• Datasets 3.0.1
• Tokenizers 0.20.0