Hugging Face's logo

sgonzalezsilot
/
speecht5_tts_voxpopuli_nl

Text-to-Speech
Transformers
TensorBoard
Safetensors
Dutch
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_voxpopuli_nl / README.md
sgonzalezsilot's picture
sgonzalezsilot
Update README.md
9447d67 verified
preview code
|
raw
history blame
1.57 kB
metadata
language:
  - nl
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS Dutch
    results: []
pipeline_tag: text-to-speech

SpeechT5 TTS Dutch

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: 0.5799

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 100
  • training_steps: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.6958 0.2151 50 0.6349
0.6574 0.4301 100 0.5799

Framework versions

  • Transformers 4.43.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1