Hugging Face's logo

trymtv
/
speecht5_tts_nps

Text-to-Audio
Transformers
PyTorch
Norwegian
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_tts_nps / README.md
trymtv's picture
trymtv
End of training
200a8ba
preview code
|
raw
history blame
1.6 kB
metadata
language:
  - 'no'
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - NbAiLab/NPSC
model-index:
  - name: speecht5_tts_npsc
    results: []

speecht5_tts_npsc

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

  • Loss: 0.4745

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
0.5489 2.42 1000 0.5087
0.5217 4.83 2000 0.4842
0.5151 7.25 3000 0.4770
0.5147 9.66 4000 0.4745

Framework versions

  • Transformers 4.34.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.14.0