Commit
·
c10fcdf
1
Parent(s):
2ea04ee
update model card README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,102 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language:
|
| 3 |
+
- el
|
| 4 |
+
license: mit
|
| 5 |
+
tags:
|
| 6 |
+
- generated_from_trainer
|
| 7 |
+
datasets:
|
| 8 |
+
- google/fleurs
|
| 9 |
+
model-index:
|
| 10 |
+
- name: SpeechT5-greek
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# SpeechT5-greek
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the FLEURS dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.3419
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 8
|
| 42 |
+
- eval_batch_size: 8
|
| 43 |
+
- seed: 42
|
| 44 |
+
- gradient_accumulation_steps: 4
|
| 45 |
+
- total_train_batch_size: 32
|
| 46 |
+
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 47 |
+
- lr_scheduler_type: linear
|
| 48 |
+
- lr_scheduler_warmup_steps: 100
|
| 49 |
+
- num_epochs: 40
|
| 50 |
+
|
| 51 |
+
### Training results
|
| 52 |
+
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 54 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
| 55 |
+
| 0.5791 | 0.99 | 106 | 0.4965 |
|
| 56 |
+
| 0.4962 | 2.0 | 213 | 0.4057 |
|
| 57 |
+
| 0.4719 | 3.0 | 320 | 0.3929 |
|
| 58 |
+
| 0.4387 | 4.0 | 427 | 0.3793 |
|
| 59 |
+
| 0.4366 | 4.99 | 533 | 0.3749 |
|
| 60 |
+
| 0.4216 | 6.0 | 640 | 0.3715 |
|
| 61 |
+
| 0.4238 | 7.0 | 747 | 0.3663 |
|
| 62 |
+
| 0.4199 | 8.0 | 854 | 0.3622 |
|
| 63 |
+
| 0.415 | 8.99 | 960 | 0.3595 |
|
| 64 |
+
| 0.409 | 10.0 | 1067 | 0.3579 |
|
| 65 |
+
| 0.4128 | 11.0 | 1174 | 0.3526 |
|
| 66 |
+
| 0.4065 | 12.0 | 1281 | 0.3554 |
|
| 67 |
+
| 0.4023 | 12.99 | 1387 | 0.3573 |
|
| 68 |
+
| 0.4028 | 14.0 | 1494 | 0.3482 |
|
| 69 |
+
| 0.407 | 15.0 | 1601 | 0.3487 |
|
| 70 |
+
| 0.4018 | 16.0 | 1708 | 0.3518 |
|
| 71 |
+
| 0.3987 | 16.99 | 1814 | 0.3483 |
|
| 72 |
+
| 0.3966 | 18.0 | 1921 | 0.3461 |
|
| 73 |
+
| 0.3931 | 19.0 | 2028 | 0.3534 |
|
| 74 |
+
| 0.3956 | 20.0 | 2135 | 0.3473 |
|
| 75 |
+
| 0.396 | 20.99 | 2241 | 0.3451 |
|
| 76 |
+
| 0.3963 | 22.0 | 2348 | 0.3435 |
|
| 77 |
+
| 0.3928 | 23.0 | 2455 | 0.3468 |
|
| 78 |
+
| 0.39 | 24.0 | 2562 | 0.3452 |
|
| 79 |
+
| 0.3875 | 24.99 | 2668 | 0.3430 |
|
| 80 |
+
| 0.405 | 26.0 | 2775 | 0.3458 |
|
| 81 |
+
| 0.3857 | 27.0 | 2882 | 0.3444 |
|
| 82 |
+
| 0.3869 | 28.0 | 2989 | 0.3436 |
|
| 83 |
+
| 0.3813 | 28.99 | 3095 | 0.3419 |
|
| 84 |
+
| 0.3859 | 30.0 | 3202 | 0.3430 |
|
| 85 |
+
| 0.3965 | 31.0 | 3309 | 0.3419 |
|
| 86 |
+
| 0.3873 | 32.0 | 3416 | 0.3432 |
|
| 87 |
+
| 0.3894 | 32.99 | 3522 | 0.3423 |
|
| 88 |
+
| 0.3855 | 34.0 | 3629 | 0.3412 |
|
| 89 |
+
| 0.3857 | 35.0 | 3736 | 0.3423 |
|
| 90 |
+
| 0.3856 | 36.0 | 3843 | 0.3420 |
|
| 91 |
+
| 0.3842 | 36.99 | 3949 | 0.3418 |
|
| 92 |
+
| 0.3827 | 38.0 | 4056 | 0.3421 |
|
| 93 |
+
| 0.389 | 39.0 | 4163 | 0.3423 |
|
| 94 |
+
| 0.3881 | 39.72 | 4240 | 0.3419 |
|
| 95 |
+
|
| 96 |
+
|
| 97 |
+
### Framework versions
|
| 98 |
+
|
| 99 |
+
- Transformers 4.30.0.dev0
|
| 100 |
+
- Pytorch 2.0.1+cu117
|
| 101 |
+
- Datasets 2.13.1
|
| 102 |
+
- Tokenizers 0.13.3
|