metadata
library_name: transformers
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_english_tehnical
results: []
speecht5_finetuned_english_tehnical
This model is a fine-tuned version of microsoft/speecht5_tts on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4447
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: 0.0001
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 8
- 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: 100
- training_steps: 1000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5826 | 0.3638 | 100 | 0.5139 |
| 0.5432 | 0.7276 | 200 | 0.4956 |
| 0.5189 | 1.0914 | 300 | 0.4836 |
| 0.5081 | 1.4552 | 400 | 0.4675 |
| 0.4982 | 1.8190 | 500 | 0.4587 |
| 0.4894 | 2.1828 | 600 | 0.4589 |
| 0.4889 | 2.5466 | 700 | 0.4530 |
| 0.4834 | 2.9104 | 800 | 0.4485 |
| 0.4768 | 3.2742 | 900 | 0.4461 |
| 0.4742 | 3.6380 | 1000 | 0.4447 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1