Inomjonov/mironshoh-speecht5-tts-0702

SpeechT5 TTS uz Mironshoh 07-02

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

• Loss: 0.5443

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 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
0.6464	0.7361	1000	0.5929
0.6096	1.4718	2000	0.5610
0.5844	2.2076	3000	0.5473
0.5986	2.9437	4000	0.5443

Framework versions

• Transformers 4.49.0.dev0
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0