Hugging Face's logo

emirhanbilgic
/
speecht5_finetuned_emirhan_tr

Text-to-Speech
TensorBoard
Safetensors
Turkish
speecht5
Generated from Trainer
turkish
Model card Files Metrics Community
speecht5_finetuned_emirhan_tr / README.md
emirhanbilgic's picture
emirhanbilgic
End of training
a597ed7 verified
preview code
|
raw
history blame
1.52 kB
metadata
license: mit
base_model: emirhanbilgic/speecht5_finetuned_emirhan_tr
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_emirhan_tr
    results: []

speecht5_finetuned_emirhan_tr

This model is a fine-tuned version of emirhanbilgic/speecht5_finetuned_emirhan_tr on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6689

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: 0.001
  • 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: 100
  • training_steps: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.6058 0.4545 100 0.6689

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1