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
da553f6
preview code
|
raw
history blame
No virus
4.64 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: 0.5093

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: 4
  • eval_batch_size: 4
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • training_steps: 15000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
No log 11.36 250 0.5773
0.6817 22.73 500 0.4226
0.6817 34.09 750 0.4172
0.4227 45.45 1000 0.4403
0.4227 56.82 1250 0.4363
0.3798 68.18 1500 0.4678
0.3798 79.55 1750 0.4609
0.3629 90.91 2000 0.4706
0.3629 102.27 2250 0.4558
0.3534 113.64 2500 0.4697
0.3534 125.0 2750 0.4641
0.3429 136.36 3000 0.4813
0.3429 147.73 3250 0.4933
0.3354 159.09 3500 0.5028
0.3354 170.45 3750 0.4860
0.3247 181.82 4000 0.4945
0.3247 193.18 4250 0.5021
0.3227 204.55 4500 0.4802
0.3227 215.91 4750 0.4874
0.3173 227.27 5000 0.4917
0.3173 238.64 5250 0.4913
0.3124 250.0 5500 0.5010
0.3124 261.36 5750 0.4846
0.3044 272.73 6000 0.5064
0.3044 284.09 6250 0.5071
0.304 295.45 6500 0.5009
0.304 306.82 6750 0.4901
0.2991 318.18 7000 0.4887
0.2991 329.55 7250 0.4908
0.2981 340.91 7500 0.4866
0.2981 352.27 7750 0.4972
0.296 363.64 8000 0.5037
0.296 375.0 8250 0.5099
0.2956 386.36 8500 0.4939
0.2956 397.73 8750 0.5055
0.2895 409.09 9000 0.5012
0.2895 420.45 9250 0.5231
0.2918 431.82 9500 0.5082
0.2918 443.18 9750 0.5120
0.289 454.55 10000 0.5067
0.289 465.91 10250 0.5097
0.287 477.27 10500 0.5244
0.287 488.64 10750 0.5116
0.2836 500.0 11000 0.5073
0.2836 511.36 11250 0.5089
0.2864 522.73 11500 0.5145
0.2864 534.09 11750 0.5077
0.2831 545.45 12000 0.5006
0.2831 556.82 12250 0.5145
0.2824 568.18 12500 0.5124
0.2824 579.55 12750 0.5166
0.2836 590.91 13000 0.5174
0.2836 602.27 13250 0.5082
0.2814 613.64 13500 0.5157
0.2814 625.0 13750 0.5210
0.2813 636.36 14000 0.5161
0.2813 647.73 14250 0.5092
0.2804 659.09 14500 0.5131
0.2804 670.45 14750 0.5128
0.2796 681.82 15000 0.5093

Framework versions

  • Transformers 4.36.0.dev0
  • Pytorch 2.1.0+cu121
  • Datasets 2.15.0
  • Tokenizers 0.14.1