Hugging Face's logo

SkylerChew
/
speecht5_tts_genshin

Text-to-Audio
Transformers
TensorBoard
Safetensors
eg
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
speecht5_tts_genshin / README.md
SkylerChew's picture
SkylerChew
End of training
9881769 verified
preview code
|
raw
history blame contribute delete
1.7 kB
metadata
library_name: transformers
language:
  - eg
license: mit
base_model: microsoft/speecht5_tts
tags:
  - generated_from_trainer
datasets:
  - simon3000/genshin-voice
model-index:
  - name: SpeechT5 TTS English Genshin
    results: []

SpeechT5 TTS English Genshin

This model is a fine-tuned version of microsoft/speecht5_tts on the genshin-voice dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5421

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: 8
  • 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: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.6689 1.9550 1000 0.5954
0.6139 3.9101 2000 0.5623
0.6054 5.8651 3000 0.5481
0.5932 7.8201 4000 0.5421

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.1
  • Tokenizers 0.19.1