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 English_Technical_data. It achieves the following results on the evaluation set:
- Loss: 0.4508
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 |
|---|---|---|---|
| 0.5468 | 0.3573 | 100 | 0.4985 |
| 0.5389 | 0.7146 | 200 | 0.4955 |
| 0.5149 | 1.0719 | 300 | 0.4767 |
| 0.5034 | 1.4292 | 400 | 0.4669 |
| 0.4961 | 1.7865 | 500 | 0.4644 |
| 0.4903 | 2.1438 | 600 | 0.4643 |
| 0.4836 | 2.5011 | 700 | 0.4587 |
| 0.4829 | 2.8584 | 800 | 0.4539 |
| 0.4752 | 3.2157 | 900 | 0.4515 |
| 0.4776 | 3.5730 | 1000 | 0.4508 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1