Hugging Face's logo

peteparker456
/
speecht5_finetuned_voxpopuli_engli

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_voxpopuli_engli / README.md
peteparker456's picture
peteparker456
peteparker456/speecht5_finetuned_voxpopuli_englishhh
d8ee313 verified
preview code
|
raw
history blame contribute delete
1.73 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_voxpopuli_engli
    results: []

speecht5_finetuned_voxpopuli_engli

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: 0.4535

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: 3e-05
  • train_batch_size: 8
  • eval_batch_size: 4
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.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: 250
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
2.0581 2.2222 500 0.4771
1.9576 4.4444 1000 0.4602
1.9343 6.6667 1500 0.4568
1.9069 8.8889 2000 0.4535

Framework versions

  • Transformers 4.47.1
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0