taohoang's picture
Update README.md
488e520
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - google/fleurs
model-index:
  - name: speecht5_finetuned_fleurs_en_us
    results: []
pipeline_tag: text-to-speech

speecht5_finetuned_fleurs_en_us

This model is a fine-tuned version of microsoft/speecht5_tts on the google/fleurs dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4831

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: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 5
  • training_steps: 54

Training results

Training Loss Epoch Step Validation Loss
0.719 0.33 9 0.5634
0.5994 0.67 18 0.5290
0.584 1.0 27 0.4924
0.5589 1.33 36 0.4828
0.5747 1.67 45 0.4848
0.5904 2.0 54 0.4831

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.3
  • Tokenizers 0.13.3