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. It achieves the following results on the evaluation set:
- Loss: 0.5090
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: 1000
- training_steps: 8000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4421 | 52.6316 | 1000 | 0.4186 |
| 0.3878 | 105.2632 | 2000 | 0.4447 |
| 0.3775 | 157.8947 | 3000 | 0.4671 |
| 0.3639 | 210.5263 | 4000 | 0.4907 |
| 0.354 | 263.1579 | 5000 | 0.4884 |
| 0.356 | 315.7895 | 6000 | 0.4997 |
| 0.3451 | 368.4211 | 7000 | 0.5021 |
| 0.3514 | 421.0526 | 8000 | 0.5090 |
Framework versions
- Transformers 4.42.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1