Hugging Face's logo

wetdog
/
speecht5_tts_openslr_ca

Text-to-Speech
Transformers
PyTorch
Catalan
speecht5
text-to-audio
TTS
Generated from Trainer
Inference Endpoints
Model card Files Community
2
speecht5_tts_openslr_ca / README.md
wetdog's picture
wetdog
End of training
fa78634
preview code
|
raw
history blame
1.65 kB
metadata
language:
  - ca
license: mit
base_model: microsoft/speecht5_tts
tags:
  - TTS
  - generated_from_trainer
datasets:
  - openslr
model-index:
  - name: SpeechT5 TTS Catalan
    results: []

SpeechT5 TTS Catalan

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

  • Loss: 0.3556

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: 5000

Training results

Training Loss Epoch Step Validation Loss
0.4295 8.55 1000 0.3828
0.4041 17.09 2000 0.3675
0.3921 25.64 3000 0.3578
0.3917 34.19 4000 0.3603
0.3725 42.74 5000 0.3556

Framework versions

  • Transformers 4.32.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3