Hugging Face's logo

Aleexc12
/
speecht5_tts_common_voice_es

Text-to-Audio
Transformers
TensorBoard
Safetensors
Spanish
speecht5
speech-synthesis
tts
spanish
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_common_voice_es / README.md
Aleexc12's picture
Aleexc12
End of training
adda59d verified
preview code
|
raw
history blame contribute delete
1.89 kB
metadata
library_name: transformers
language:
  - es
license: mit
base_model: microsoft/speecht5_tts
tags:
  - speech-synthesis
  - tts
  - spanish
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_13_0
model-index:
  - name: SpeechT5 TTS Espanol
    results: []

SpeechT5 TTS Espanol

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

  • Loss: 0.4665

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: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • 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
0.5511 1.0941 1000 0.4901
0.515 2.1883 2000 0.4760
0.5032 3.2824 3000 0.4707
0.5076 4.3766 4000 0.4665

Framework versions

  • Transformers 4.47.0.dev0
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.1