speech-t5-ur / README.md
mwz's picture
Update README.md
3d15071 verified
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - fleurs
model-index:
  - name: ft-speech-t5-on-voxpopuli
    results: []
language:
  - ur

ft-speech-t5-on-voxpopuli

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

  • Loss: 0.5187

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: 50
  • training_steps: 100
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.7238 0.84 50 0.5677
0.6067 1.68 100 0.5185

Framework versions

  • Transformers 4.35.2
  • Pytorch 2.1.2
  • Datasets 2.15.0
  • Tokenizers 0.15.2