Hugging Face's logo

Moustapha91
/
speecht5_finetuned_wo_v2

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_finetuned_wo_v2 / README.md
Moustapha91's picture
Moustapha91
End of training
2c30a00 verified
preview code
|
raw
history blame
1.58 kB
metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_finetuned_wo_v2
    results: []

speecht5_finetuned_wo_v2

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: 0.3877

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: 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: 5000
  • training_steps: 9000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4585 7.1111 3000 0.4186
0.4252 14.2222 6000 0.3937
0.4198 21.3333 9000 0.3877

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.0
  • Datasets 3.0.0
  • Tokenizers 0.19.1