InZaneManInAZuite/SpeechT5_TTS_LJSpeech_Test

SpeechT5 TTS LJSPeech English

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

• Loss: 0.3753

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: Use OptimizerNames.ADAMW_TORCH_FUSED 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: 500
• training_steps: 4000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
0.8718	2.7110	1000	0.3896
0.8247	5.4206	2000	0.3795
0.8214	8.1303	3000	0.3761
0.8261	10.8412	4000	0.3753

Framework versions

• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 3.6.0
• Tokenizers 0.22.2