Edit model card

speecht5_finetuned_male_globo_add_token_3_commonvoice_1

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3535

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: 500
  • training_steps: 10000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4234 1.96 1000 0.3852
0.4022 3.91 2000 0.3719
0.3845 5.87 3000 0.3663
0.3838 7.83 4000 0.3620
0.3818 9.79 5000 0.3614
0.3798 11.74 6000 0.3590
0.3748 13.7 7000 0.3565
0.3734 15.66 8000 0.3549
0.3766 17.62 9000 0.3535
0.3753 19.57 10000 0.3535

Framework versions

  • Transformers 4.39.0.dev0
  • Pytorch 2.2.1
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
8
Safetensors
Model size
144M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.