Hugging Face's logo

JFuellem
/
speecht5_finetuned_voxpopuli_de

Text-to-Speech
Transformers
PyTorch
TensorBoard
German
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
speecht5_finetuned_voxpopuli_de / README.md
JFuellem's picture
JFuellem
Update README.md
a246a9f
preview code
|
raw
history blame contribute delete
1.73 kB
metadata
language:
  - de
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 finetuned with german VoxPopuli subset (13961) - JFuellem
    results: []
pipeline_tag: text-to-speech

SpeechT5 finetuned with german VoxPopuli subset (13961) - JFuellem

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

  • Loss: 0.4670

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

Training results

Training Loss Epoch Step Validation Loss
0.5294 2.55 1000 0.4873
0.5078 5.09 2000 0.4737
0.5061 7.64 3000 0.4685
0.5085 10.19 4000 0.4670

Framework versions

  • Transformers 4.31.0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3