fil_b32_le5_s4000 / README.md
mikhail-panzo's picture
End of training
5013402 verified
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: fil_b32_le5_s4000
    results: []

fil_b32_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: 0.4102

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: 8
  • 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
0.5539 44.4444 500 0.4850
0.4867 88.8889 1000 0.4439
0.4595 133.3333 1500 0.4245
0.4395 177.7778 2000 0.4155
0.4327 222.2222 2500 0.4121
0.4279 266.6667 3000 0.4127
0.4202 311.1111 3500 0.4098
0.4167 355.5556 4000 0.4102

Framework versions

  • Transformers 4.41.0.dev0
  • Pytorch 2.2.1+cu121
  • Datasets 2.19.0
  • Tokenizers 0.19.1