speecht5_finetuned_lowdata

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: 0.4446

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
0.5558	4.1026	100	0.4981
0.5053	8.2051	200	0.4659
0.4692	12.3077	300	0.4616
0.4552	16.4103	400	0.4532
0.4412	20.5128	500	0.4472
0.4275	24.6154	600	0.4470
0.4253	28.7179	700	0.4501
0.4139	32.8205	800	0.4459
0.4142	36.9231	900	0.4458
0.4053	41.0256	1000	0.4446

Framework versions

• Transformers 4.46.3
• Pytorch 2.5.1+cu121
• Datasets 3.2.0
• Tokenizers 0.20.3