Hugging Face's logo

Dawid511
/
speecht5_finetuned_librispeech_polish

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_librispeech_polish / README.md
Dawid511's picture
Dawid511
End of training
ccaa143 verified
preview code
|
raw
history blame contribute delete
1.77 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_librispeech_polish
    results: []

speecht5_finetuned_librispeech_polish

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: 0.3712

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
0.4598 1.3851 100 0.4189
0.4308 2.7703 200 0.3925
0.4123 4.1589 300 0.3818
0.4004 5.5440 400 0.3754
0.3973 6.9292 500 0.3712

Framework versions

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