Hugging Face's logo

deryauysal
/
speechT5_tts_openSLR_tr

Text-to-Speech
Transformers
PyTorch
Turkish
speecht5
text-to-audio
turkish
speech-generation
generated_from_trainer
Inference Endpoints
Model card Files Community
speechT5_tts_openSLR_tr / README.md
deryauysal's picture
deryauysal
End of training
3261f36
preview code
|
raw history blame contribute delete
No virus
1.67 kB
metadata
language:
  - tr
license: mit
base_model: microsoft/speecht5_tts
tags:
  - text-to-speech
  - turkish
  - speech-generation
  - generated_from_trainer
datasets:
  - openSLR
model-index:
  - name: SpeechT5 TTS Turkish with openSLR
    results: []

SpeechT5 TTS Turkish with openSLR

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

  • Loss: 0.4350

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
0.497 51.28 1000 0.4593
0.4528 102.56 2000 0.4449
0.4577 153.85 3000 0.4401
0.4459 205.13 4000 0.4350

Framework versions

  • Transformers 4.33.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3