Hugging Face's logo

mohammadhossein
/
speecht5_tts_data

Text-to-Audio
Transformers
PyTorch
pe
speecht5
mhs
Generated from Trainer
Inference Endpoints
Model card Files Community
1
speecht5_tts_data / README.md
mohammadhossein's picture
mohammadhossein
End of training
62a543e
preview code
|
raw
history blame contribute delete
1.62 kB
metadata
language:
  - pe
license: mit
base_model: microsoft/speecht5_tts
tags:
  - mhs
  - generated_from_trainer
datasets:
  - persian_tts_data
model-index:
  - name: SpeechT5 TTS persian
    results: []

SpeechT5 TTS persian

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

  • Loss: 0.3811

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

Training results

Training Loss Epoch Step Validation Loss
0.4521 5.05 1000 0.4051
0.4279 10.1 2000 0.3892
0.4198 15.15 3000 0.3826
0.4159 20.2 4000 0.3811

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.4
  • Tokenizers 0.13.3