Hugging Face's logo

FredDYyy
/
speecht5_finetuned_voxpopuli_nl

Text-to-Audio
Transformers
TensorBoard
Safetensors
Dutch
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_voxpopuli_nl / README.md
FredDYyy's picture
FredDYyy
End of training
fefd476 verified
preview code
|
raw
history blame contribute delete
1.66 kB
metadata
language:
  - nl
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: Speecht5 finetuned nl - FredDYyy
    results: []

Speecht5 finetuned nl - FredDYyy

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: 0.4734

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: 8
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 250
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5332 5.66 500 0.4933
0.5219 11.32 1000 0.4798
0.5078 16.97 1500 0.4745
0.4991 22.63 2000 0.4734

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.1.2
  • Datasets 2.18.0
  • Tokenizers 0.15.2