ceb_b64_le5_s4000 / README.md
mikhail-panzo's picture
End of training
b13185e verified
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: ceb_b64_le5_s4000
    results: []

ceb_b64_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: 0.3942

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: 4
  • total_train_batch_size: 64
  • 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
0.536 19.8020 500 0.4640
0.4674 39.6040 1000 0.4247
0.4479 59.4059 1500 0.4102
0.4356 79.2079 2000 0.4032
0.4277 99.0099 2500 0.3962
0.418 118.8119 3000 0.3955
0.4162 138.6139 3500 0.3940
0.4082 158.4158 4000 0.3942

Framework versions

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