uz-speecht5-finetuned

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: 0.4253

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: 4
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 8
• 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: 100
• training_steps: 2000
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss
4.8912	1.4628	200	0.5255
4.3184	2.9256	400	0.4803
4.2157	4.3820	600	0.4550
4.0862	5.8448	800	0.4520
3.8760	7.3012	1000	0.4366
3.8867	8.7640	1200	0.4335
3.8045	10.2204	1400	0.4337
3.7306	11.6832	1600	0.4283
3.6026	13.1396	1800	0.4262
3.6685	14.6024	2000	0.4253

Framework versions

• Transformers 5.15.0.dev0
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.22.2