Hugging Face's logo

Sandiago21
/
speecht5_finetuned_google_fleurs_greek

Text-to-Speech
Transformers
PyTorch
TensorBoard
Safetensors
speecht5
text-to-audio
Generated from Trainer
Model card Files
xet
 Metrics Community
2
Sandiago21 commited on
Commit
9dfd004
·
1 Parent(s): f84b629

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +51 -50
README.md CHANGED
@@ -1,23 +1,24 @@
1
  ---
 
 
2
  license: mit
3
  tags:
4
  - generated_from_trainer
5
  datasets:
6
- - fleurs
7
  model-index:
8
- - name: speecht5_finetuned_google_fleurs_greek
9
  results: []
10
- pipeline_tag: text-to-speech
11
  ---
12
 
13
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
14
  should probably proofread and complete it, then remove this comment. -->
15
 
16
- # speecht5_finetuned_google_fleurs_greek
17
 
18
- This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the fleurs dataset.
19
  It achieves the following results on the evaluation set:
20
- - Loss: 0.3419
21
 
22
  ## Model description
23
 
@@ -36,7 +37,7 @@ More information needed
36
  ### Training hyperparameters
37
 
38
  The following hyperparameters were used during training:
39
- - learning_rate: 1e-05
40
  - train_batch_size: 8
41
  - eval_batch_size: 8
42
  - seed: 42
@@ -49,48 +50,48 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-----:|:----:|:---------------:|
54
- | 0.5791 | 0.99 | 106 | 0.4965 |
55
- | 0.4962 | 2.0 | 213 | 0.4057 |
56
- | 0.4719 | 3.0 | 320 | 0.3929 |
57
- | 0.4387 | 4.0 | 427 | 0.3793 |
58
- | 0.4366 | 4.99 | 533 | 0.3749 |
59
- | 0.4216 | 6.0 | 640 | 0.3715 |
60
- | 0.4238 | 7.0 | 747 | 0.3663 |
61
- | 0.4199 | 8.0 | 854 | 0.3622 |
62
- | 0.415 | 8.99 | 960 | 0.3595 |
63
- | 0.409 | 10.0 | 1067 | 0.3579 |
64
- | 0.4128 | 11.0 | 1174 | 0.3526 |
65
- | 0.4065 | 12.0 | 1281 | 0.3554 |
66
- | 0.4023 | 12.99 | 1387 | 0.3573 |
67
- | 0.4028 | 14.0 | 1494 | 0.3482 |
68
- | 0.407 | 15.0 | 1601 | 0.3487 |
69
- | 0.4018 | 16.0 | 1708 | 0.3518 |
70
- | 0.3987 | 16.99 | 1814 | 0.3483 |
71
- | 0.3966 | 18.0 | 1921 | 0.3461 |
72
- | 0.3931 | 19.0 | 2028 | 0.3534 |
73
- | 0.3956 | 20.0 | 2135 | 0.3473 |
74
- | 0.396 | 20.99 | 2241 | 0.3451 |
75
- | 0.3963 | 22.0 | 2348 | 0.3435 |
76
- | 0.3928 | 23.0 | 2455 | 0.3468 |
77
- | 0.39 | 24.0 | 2562 | 0.3452 |
78
- | 0.3875 | 24.99 | 2668 | 0.3430 |
79
- | 0.405 | 26.0 | 2775 | 0.3458 |
80
- | 0.3857 | 27.0 | 2882 | 0.3444 |
81
- | 0.3869 | 28.0 | 2989 | 0.3436 |
82
- | 0.3813 | 28.99 | 3095 | 0.3419 |
83
- | 0.3859 | 30.0 | 3202 | 0.3430 |
84
- | 0.3965 | 31.0 | 3309 | 0.3419 |
85
- | 0.3873 | 32.0 | 3416 | 0.3432 |
86
- | 0.3894 | 32.99 | 3522 | 0.3423 |
87
- | 0.3855 | 34.0 | 3629 | 0.3412 |
88
- | 0.3857 | 35.0 | 3736 | 0.3423 |
89
- | 0.3856 | 36.0 | 3843 | 0.3420 |
90
- | 0.3842 | 36.99 | 3949 | 0.3418 |
91
- | 0.3827 | 38.0 | 4056 | 0.3421 |
92
- | 0.389 | 39.0 | 4163 | 0.3423 |
93
- | 0.3881 | 39.72 | 4240 | 0.3419 |
94
 
95
 
96
  ### Framework versions
@@ -98,4 +99,4 @@ The following hyperparameters were used during training:
98
  - Transformers 4.30.0.dev0
99
  - Pytorch 2.0.1+cu117
100
  - Datasets 2.13.1
101
- - Tokenizers 0.13.3
 
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: 0.3920
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 2.5e-05
41
  - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
 
50
 
51
  ### Training results
52
 
53
+ | Training Loss | Epoch | Step | Validation Loss |
54
+ |:-------------:|:-----:|:-----:|:---------------:|
55
+ | 0.5174 | 1.0 | 583 | 0.4863 |
56
+ | 0.4948 | 2.0 | 1166 | 0.4611 |
57
+ | 0.4723 | 3.0 | 1749 | 0.4503 |
58
+ | 0.4763 | 4.0 | 2333 | 0.4438 |
59
+ | 0.4614 | 5.0 | 2916 | 0.4407 |
60
+ | 0.4569 | 6.0 | 3499 | 0.4387 |
61
+ | 0.4538 | 7.0 | 4082 | 0.4306 |
62
+ | 0.4539 | 8.0 | 4666 | 0.4282 |
63
+ | 0.4564 | 9.0 | 5249 | 0.4230 |
64
+ | 0.4493 | 10.0 | 5832 | 0.4222 |
65
+ | 0.445 | 11.0 | 6415 | 0.4190 |
66
+ | 0.4564 | 12.0 | 6999 | 0.4195 |
67
+ | 0.4381 | 13.0 | 7582 | 0.4161 |
68
+ | 0.4328 | 14.0 | 8165 | 0.4147 |
69
+ | 0.4424 | 15.0 | 8748 | 0.4140 |
70
+ | 0.4282 | 16.0 | 9332 | 0.4117 |
71
+ | 0.4349 | 17.0 | 9915 | 0.4090 |
72
+ | 0.4381 | 18.0 | 10498 | 0.4090 |
73
+ | 0.4328 | 19.0 | 11081 | 0.4073 |
74
+ | 0.4347 | 20.0 | 11665 | 0.4079 |
75
+ | 0.4293 | 21.0 | 12248 | 0.4055 |
76
+ | 0.4251 | 22.0 | 12831 | 0.4052 |
77
+ | 0.4359 | 23.0 | 13414 | 0.4023 |
78
+ | 0.4311 | 24.0 | 13998 | 0.4016 |
79
+ | 0.421 | 25.0 | 14581 | 0.4014 |
80
+ | 0.4162 | 26.0 | 15164 | 0.3991 |
81
+ | 0.4219 | 27.0 | 15747 | 0.3990 |
82
+ | 0.4247 | 28.0 | 16331 | 0.3989 |
83
+ | 0.4188 | 29.0 | 16914 | 0.3974 |
84
+ | 0.4229 | 30.0 | 17497 | 0.3976 |
85
+ | 0.4246 | 31.0 | 18080 | 0.3960 |
86
+ | 0.4219 | 32.0 | 18664 | 0.3956 |
87
+ | 0.4228 | 33.0 | 19247 | 0.3951 |
88
+ | 0.4183 | 34.0 | 19830 | 0.3946 |
89
+ | 0.4097 | 35.0 | 20413 | 0.3936 |
90
+ | 0.4245 | 36.0 | 20997 | 0.3935 |
91
+ | 0.4184 | 37.0 | 21580 | 0.3930 |
92
+ | 0.4198 | 38.0 | 22163 | 0.3937 |
93
+ | 0.4193 | 39.0 | 22746 | 0.3925 |
94
+ | 0.4096 | 39.98 | 23320 | 0.3920 |
95
 
96
 
97
  ### Framework versions
 
99
  - Transformers 4.30.0.dev0
100
  - Pytorch 2.0.1+cu117
101
  - Datasets 2.13.1
102
+ - Tokenizers 0.13.3