Hugging Face's logo

dirichletian
/
speecht5_tts_voxpopuli_nl_four

Text-to-Audio
Transformers
PyTorch
Dutch
speecht5
jjbj
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_tts_voxpopuli_nl_four / README.md
dirichletian's picture
dirichletian
End of training
dbc2e84
preview code
|
raw
history blame contribute delete
1.6 kB
metadata
language:
  - nl
license: mit
base_model: microsoft/speecht5_tts
tags:
  - jjbj
  - generated_from_trainer
datasets:
  - amharic_parallel
model-index:
  - name: SpeechT5 TTS Amh
    results: []

SpeechT5 TTS Amh

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

  • Loss: 0.3694

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
0.426 3.32 1000 0.3915
0.4049 6.64 2000 0.3776
0.394 9.96 3000 0.3719
0.3947 13.28 4000 0.3694

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3