BanUrsus's picture
End of training
ca3153f verified
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - voxpopuli
model-index:
  - name: speecht5-ft-voxpopuli-nl
    results: []

speecht5-ft-voxpopuli-nl

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

  • Loss: 0.4540

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: 8
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • 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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5096 8.6 1000 0.4712
0.4863 17.2 2000 0.4594
0.4876 25.81 3000 0.4565
0.4791 34.41 4000 0.4540

Framework versions

  • Transformers 4.39.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.1