Hugging Face's logo

zongxiao
/
speecht5_finetuned_zh-TW

Text-to-Audio
Transformers
PyTorch
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
speecht5_finetuned_zh-TW / README.md
zongxiao's picture
zongxiao
End of training
6a04cd5
preview code
|
raw
history blame contribute delete
1.63 kB
metadata
license: mit
base_model: GCYY/speecht5_finetuned_fleurs_zh
tags:
  - generated_from_trainer
datasets:
  - common_voice_13_0
model-index:
  - name: speecht5_finetuned_zh-TW
    results: []

speecht5_finetuned_zh-TW

This model is a fine-tuned version of GCYY/speecht5_finetuned_fleurs_zh on the common_voice_13_0 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5108

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: 4
  • 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: 4000

Training results

Training Loss Epoch Step Validation Loss
0.5844 6.62 1000 0.5454
0.5495 13.25 2000 0.5215
0.5536 19.87 3000 0.5176
0.5257 26.49 4000 0.5108

Framework versions

  • Transformers 4.33.3
  • Pytorch 2.0.1
  • Datasets 2.14.5
  • Tokenizers 0.13.3