metadata
library_name: transformers
license: mit
base_model: Timmyafolami/speecht5_female_british_english
tags:
- generated_from_trainer
model-index:
- name: speecht5_female_british_english_1
results: []
speecht5_female_british_english_1
This model is a fine-tuned version of Timmyafolami/speecht5_female_british_english on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4200
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: 2
- 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 |
|---|---|---|---|
| 0.4698 | 0.4890 | 100 | 0.4438 |
| 0.4769 | 0.9780 | 200 | 0.4457 |
| 0.4529 | 1.4670 | 300 | 0.4540 |
| 0.4553 | 1.9560 | 400 | 0.4345 |
| 0.4522 | 2.4450 | 500 | 0.4331 |
| 0.4539 | 2.9340 | 600 | 0.4259 |
| 0.4462 | 3.4230 | 700 | 0.4236 |
| 0.4408 | 3.9120 | 800 | 0.4333 |
| 0.4286 | 4.4010 | 900 | 0.4167 |
| 0.4294 | 4.8900 | 1000 | 0.4200 |
Framework versions
- Transformers 4.45.1
- Pytorch 2.1.0+cu118
- Datasets 3.0.1
- Tokenizers 0.20.0