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
291dc9d
preview code
|
raw
history blame
No virus
1.78 kB
metadata
language:
  - en
license: mit
base_model: microsoft/speecht5_tts
tags:
  - en_accent,mozilla,t5,common_voice_1_0
  - generated_from_trainer
datasets:
  - mozilla-foundation/common_voice_1_0
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 Common Voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5103

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: 16
  • 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
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.5407 16.0 1000 0.4686
0.4995 32.0 2000 0.4828
0.4729 48.0 3000 0.4939
0.4733 64.0 4000 0.5020
0.4901 80.0 5000 0.5103

Framework versions

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