Hugging Face's logo

abdelkader12
/
Text_To_Speech_model

Text-to-Audio
Transformers
TensorBoard
Safetensors
Arabic
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Text_To_Speech_model / README.md
abdelkader12's picture
abdelkader12
End of training
1992bae verified
preview code
|
raw
history blame contribute delete
1.75 kB
metadata
library_name: transformers
language:
  - ar
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - speechbrain/spkrec-xvect-voxceleb
model-index:
  - name: Speech 5
    results: []

Speech 5

This model is a fine-tuned version of microsoft/speecht5_tts on the Darija Common Voice 11.0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3400

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: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • 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
0.2289 57.1429 100 0.3906
0.2089 114.2857 200 0.3636
0.1927 171.4286 300 0.3515
0.1855 228.5714 400 0.3444
0.1864 285.7143 500 0.3400

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1