Hugging Face's logo

Inomjonov
/
speecht5-finetuned-uzbek-1102

Text-to-Audio
Transformers
TensorBoard
Safetensors
Uzbek
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5-finetuned-uzbek-1102 / README.md
Inomjonov's picture
Inomjonov
End of training
de60c62 verified
preview code
|
raw
history blame contribute delete
1.66 kB
metadata
library_name: transformers
language:
  - uz
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - Beehzod/aug_uzbek_dataset
model-index:
  - name: Mironshoh uzbek tts
    results: []

Mironshoh uzbek tts

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

  • Loss: 0.4046

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: 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: 50
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.429 17.5499 1000 0.4077
0.4052 35.0887 2000 0.4046

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.5.1+cu124
  • Datasets 3.2.0
  • Tokenizers 0.21.0