Hugging Face's logo

Wsassi
/
speecht5_finetuned_polyAi

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_polyAi / README.md
Wsassi's picture
Wsassi
End of training
002be70 verified
preview code
|
raw history blame contribute delete
No virus
1.57 kB
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - minds14
model-index:
  - name: speecht5_finetuned_polyAi
    results: []

speecht5_finetuned_polyAi

This model is a fine-tuned version of microsoft/speecht5_tts on the minds14 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6495

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: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.6267 1.0 124 1.0811
0.9903 2.0 248 0.7723
0.95 3.0 372 0.7042
0.8184 4.0 496 0.6570
0.7998 5.0 620 0.6495

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1