metadata
license: mit
base_model: microsoft/speecht5_tts
tags:
- generated_from_trainer
model-index:
- name: speecht5_finetuned_wo_v1
results: []
speecht5_finetuned_wo_v1
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: 0.3364
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: 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: 5000
- training_steps: 7000
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4494 | 2.8219 | 1000 | 0.3897 |
| 0.4043 | 5.6437 | 2000 | 0.3628 |
| 0.3852 | 8.4656 | 3000 | 0.3500 |
| 0.3756 | 11.2875 | 4000 | 0.3447 |
| 0.3666 | 14.1093 | 5000 | 0.3408 |
| 0.3575 | 16.9312 | 6000 | 0.3375 |
| 0.354 | 19.7531 | 7000 | 0.3364 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1