Hugging Face's logo

bregsi
/
speecht5_finetuned_voxpopuli_de

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_voxpopuli_de / README.md
bregsi's picture
bregsi
End of training
c3608ea verified
preview code
|
raw
history blame contribute delete
1.65 kB
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - voxpopuli
model-index:
  - name: speecht5_finetuned_voxpopuli_de
    results: []

speecht5_finetuned_voxpopuli_de

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: 0.4627

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: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5277 2.2812 1000 0.4833
0.51 4.5623 2000 0.4696
0.5052 6.8435 3000 0.4638
0.4996 9.1246 4000 0.4627

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1