Hugging Face's logo

Predict9731
/
speecht5_tts_voxpopuli_cs

Text-to-Audio
Transformers
Safetensors
Czech
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_tts_voxpopuli_cs / README.md
Predict9731's picture
Predict9731
Update README.md
0c7b17e
preview code
|
raw
history blame contribute delete
1.65 kB
metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - voxpopuli
model-index:
  - name: speecht5_tts_voxpopuli_cs
    results: []
language:
  - cs

speecht5_tts_voxpopuli_cs

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: 0.4382

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: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5186 0.89 1000 0.4621
0.4844 1.78 2000 0.4437
0.4851 2.68 3000 0.4404
0.4799 3.57 4000 0.4382

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.1
  • Tokenizers 0.15.0