Edit model card

ceb_b128_le5_s4000

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: 0.3943

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: 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5272 39.2157 500 0.4584
0.4634 78.4314 1000 0.4220
0.4466 117.6471 1500 0.4104
0.4289 156.8627 2000 0.4017
0.4223 196.0784 2500 0.3969
0.4149 235.2941 3000 0.3960
0.4129 274.5098 3500 0.3962
0.4108 313.7255 4000 0.3943

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