leofltt's picture
Update README.md
37f61cf verified
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: speecht5_quick_finetuned_voxpopuli_it
    results: []
pipeline_tag: text-to-speech

speecht5_quick_finetuned_voxpopuli_it

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

  • Loss: 0.4879

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: 250
  • training_steps: 2500
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5535 1.53 250 0.5129
0.5395 3.07 500 0.5065
0.5393 4.6 750 0.4994
0.5316 6.13 1000 0.4956
0.5372 7.66 1250 0.4919
0.53 9.2 1500 0.4914
0.5277 10.73 1750 0.4888
0.5198 12.26 2000 0.4896
0.5236 13.79 2250 0.4880
0.5209 15.33 2500 0.4879

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2