|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- fleurs |
|
model-index: |
|
- name: speecht5_finetuned_google_fleurs_greek |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# speecht5_finetuned_google_fleurs_greek |
|
|
|
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the fleurs dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3419 |
|
|
|
## 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: 8 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 4 |
|
- 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 |
|
- num_epochs: 40 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:-----:|:----:|:---------------:| |
|
| 0.5791 | 0.99 | 106 | 0.4965 | |
|
| 0.4962 | 2.0 | 213 | 0.4057 | |
|
| 0.4719 | 3.0 | 320 | 0.3929 | |
|
| 0.4387 | 4.0 | 427 | 0.3793 | |
|
| 0.4366 | 4.99 | 533 | 0.3749 | |
|
| 0.4216 | 6.0 | 640 | 0.3715 | |
|
| 0.4238 | 7.0 | 747 | 0.3663 | |
|
| 0.4199 | 8.0 | 854 | 0.3622 | |
|
| 0.415 | 8.99 | 960 | 0.3595 | |
|
| 0.409 | 10.0 | 1067 | 0.3579 | |
|
| 0.4128 | 11.0 | 1174 | 0.3526 | |
|
| 0.4065 | 12.0 | 1281 | 0.3554 | |
|
| 0.4023 | 12.99 | 1387 | 0.3573 | |
|
| 0.4028 | 14.0 | 1494 | 0.3482 | |
|
| 0.407 | 15.0 | 1601 | 0.3487 | |
|
| 0.4018 | 16.0 | 1708 | 0.3518 | |
|
| 0.3987 | 16.99 | 1814 | 0.3483 | |
|
| 0.3966 | 18.0 | 1921 | 0.3461 | |
|
| 0.3931 | 19.0 | 2028 | 0.3534 | |
|
| 0.3956 | 20.0 | 2135 | 0.3473 | |
|
| 0.396 | 20.99 | 2241 | 0.3451 | |
|
| 0.3963 | 22.0 | 2348 | 0.3435 | |
|
| 0.3928 | 23.0 | 2455 | 0.3468 | |
|
| 0.39 | 24.0 | 2562 | 0.3452 | |
|
| 0.3875 | 24.99 | 2668 | 0.3430 | |
|
| 0.405 | 26.0 | 2775 | 0.3458 | |
|
| 0.3857 | 27.0 | 2882 | 0.3444 | |
|
| 0.3869 | 28.0 | 2989 | 0.3436 | |
|
| 0.3813 | 28.99 | 3095 | 0.3419 | |
|
| 0.3859 | 30.0 | 3202 | 0.3430 | |
|
| 0.3965 | 31.0 | 3309 | 0.3419 | |
|
| 0.3873 | 32.0 | 3416 | 0.3432 | |
|
| 0.3894 | 32.99 | 3522 | 0.3423 | |
|
| 0.3855 | 34.0 | 3629 | 0.3412 | |
|
| 0.3857 | 35.0 | 3736 | 0.3423 | |
|
| 0.3856 | 36.0 | 3843 | 0.3420 | |
|
| 0.3842 | 36.99 | 3949 | 0.3418 | |
|
| 0.3827 | 38.0 | 4056 | 0.3421 | |
|
| 0.389 | 39.0 | 4163 | 0.3423 | |
|
| 0.3881 | 39.72 | 4240 | 0.3419 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.30.0.dev0 |
|
- Pytorch 2.0.1+cu117 |
|
- Datasets 2.13.1 |
|
- Tokenizers 0.13.3 |
|
|
