deryauysal's picture
End of training
8ecc78a
metadata
language:
  - tr
license: mit
base_model: microsoft/speecht5_tts
tags:
  - text-to-speech
  - turkish
  - speech-generation
  - generated_from_trainer
datasets:
  - common_voice
model-index:
  - name: SpeechT5 TTS Turkish
    results: []

SpeechT5 TTS Turkish

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

  • Loss: 0.4650

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
0.4726 111.11 1000 0.4570
0.4333 222.22 2000 0.4567
0.417 333.33 3000 0.4631
0.4327 444.44 4000 0.4650

Framework versions

  • Transformers 4.33.0.dev0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.4
  • Tokenizers 0.13.3