Hugging Face's logo

maghrane
/
speecht5_finetuned_marar

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_marar / README.md
maghrane's picture
maghrane
End of training
c96bad7 verified
preview code
|
raw
history blame contribute delete
1.76 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_marar
    results: []

speecht5_finetuned_marar

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

  • Loss: 0.5149

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: 0.0001
  • train_batch_size: 4
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 8
  • total_train_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • training_steps: 500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.7185 3.1873 100 0.6770
0.5988 6.3745 200 0.5643
0.5588 9.5618 300 0.5402
0.5412 12.7490 400 0.5194
0.5154 15.9363 500 0.5149

Framework versions

  • Transformers 4.46.2
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3