glaswegian_tts / README.md
divakaivan's picture
Update README.md
7f1f305 verified
|
raw
history blame
1.47 kB
metadata
language:
  - en
license: mit
base_model: microsoft/speecht5_tts
tags:
  - scottish
  - tts
  - glaswegian
  - generated_from_trainer
datasets:
  - divakaivan/glaswegian_audio
model-index:
  - name: GlaswegianTTS v0.1.0
    results: []

GlaswegianTTS v0.1.0

This model is a fine-tuned version of microsoft/speecht5_tts on the glaswegian_tts_v0.1.0 dataset.

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: 1000
  • training_steps: 4000
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
0.4348 125.0 1000 0.4666
0.3783 250.0 2000 0.4955
0.3715 375.0 3000 0.5152
0.3564 500.0 4000 0.5275

Framework versions

  • Transformers 4.42.0.dev0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1