Hugging Face's logo

zongxiao
/
speecht5_tts_voxpopuli_nl_2

Text-to-Speech
Transformers
PyTorch
Dutch
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Community
1
speecht5_tts_voxpopuli_nl_2 / README.md
zongxiao's picture
zongxiao
End of training
6a26f9a
preview code
|
raw
history blame contribute delete
1.61 kB
metadata
language:
  - nl
license: mit
base_model: microsoft/speecht5_tts
tags:
  - text-to-speech
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS Dutch
    results: []

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: 0.4491

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-06
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 4
  • 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: 2000

Training results

Training Loss Epoch Step Validation Loss
0.4883 2.15 500 0.4505
0.4856 4.3 1000 0.4503
0.4896 6.45 1500 0.4500
0.4912 8.6 2000 0.4491

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1
  • Datasets 2.14.5
  • Tokenizers 0.13.3