Hugging Face's logo

JBZhang2342
/
speecht5_tts

Text-to-Audio
Transformers
TensorBoard
Safetensors
English
speecht5
en_accent,mozilla,t5,common_voice_1_0
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts / README.md
JBZhang2342's picture
JBZhang2342
End of training
cea3158
preview code
|
raw
history blame
1.69 kB
metadata
language:
  - en
license: mit
base_model: microsoft/speecht5_tts
tags:
  - en_accent,vocpopuli,t5
  - generated_from_trainer
datasets:
  - facebook/voxpopuli
model-index:
  - name: SpeechT5 TTS English Accented
    results: []

SpeechT5 TTS English Accented

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: 0.4868

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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5417 8.0 1000 0.4919
0.4956 16.0 2000 0.4833
0.4774 24.0 3000 0.4824
0.482 32.0 4000 0.4868

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.14.6
  • Tokenizers 0.14.1