Edit model card

ceb_b128_le3_s8000

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: 1.4349

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: 0.001
  • train_batch_size: 32
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 2000
  • training_steps: 8000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4379 39.2157 500 0.4143
0.4492 78.4314 1000 0.4377
1.4417 117.6471 1500 1.4372
1.4311 156.8627 2000 1.4308
1.4506 196.0784 2500 1.4365
1.4286 235.2941 3000 1.4312
1.4285 274.5098 3500 1.4329
1.421 313.7255 4000 1.4406
1.4228 352.9412 4500 1.4337
1.4232 392.1569 5000 1.4328
1.4208 431.3725 5500 1.4331
1.4211 470.5882 6000 1.4311
1.4204 509.8039 6500 1.4344
1.4196 549.0196 7000 1.4362
1.4194 588.2353 7500 1.4361
1.4184 627.4510 8000 1.4349

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
144M params
Tensor type
F32
·

Finetuned from