perisolb's picture
speecht5_tts_nst_no_experiment
28f5a68
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
model-index:
  - name: speecht5_tts_nst_no_experiment
    results: []

speecht5_tts_nst_no_experiment

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

  • Loss: 0.3325

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: 16
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • 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: 4000

Training results

Training Loss Epoch Step Validation Loss
0.3951 6.67 1000 0.3540
0.3689 13.33 2000 0.3422
0.361 20.0 3000 0.3332
0.3603 26.67 4000 0.3325

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3