Hugging Face's logo

Daniel981215
/
speecht5-text-to-speech-voxpopuli-nl

Text-to-Speech
Transformers
TensorBoard
Safetensors
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5-text-to-speech-voxpopuli-nl / README.md
Daniel981215's picture
Daniel981215
Update README.md
846bb5e verified
preview code
|
raw
history blame
1.59 kB
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - facebook/voxpopuli-nl
model-index:
  - name: speecht5_finetuned_voxpopuli_nl
    results: []
pipeline_tag: text-to-speech

speecht5_finetuned_voxpopuli_nl

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

  • Loss: 0.4969

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: 800
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5609 12.5 400 0.5169
0.5262 25.0 800 0.4969

Framework versions

  • Transformers 4.37.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.16.1
  • Tokenizers 0.15.0