Hugging Face's logo

Avitas8485
/
speecht5_tts_commonvoice_en_04

Text-to-Speech
Transformers
PyTorch
TensorBoard
English
speecht5
text-to-audio
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
1
speecht5_tts_commonvoice_en_04 / README.md
Avitas8485's picture
Avitas8485
update model card README.md
5188b2e
preview code
|
raw
history blame
1.59 kB
metadata
language:
  - en
license: mit
tags:
  - text-to-speech
  - generated_from_trainer
datasets:
  - gigaspeech
model-index:
  - name: speecht5_tts_commonvoice_en_04_test
    results: []

speecht5_tts_commonvoice_en_04_test

This model is a fine-tuned version of Avitas8485/speecht5_tts_commonvoice_en_03 on the gigaspeech dataset. It achieves the following results on the evaluation set:

  • Loss: 0.4270

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: 8
  • eval_batch_size: 8
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 2000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4662 1.95 1000 0.4328
0.465 3.9 2000 0.4270

Framework versions

  • Transformers 4.30.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.13.0
  • Tokenizers 0.13.3