Hugging Face's logo

Mohsen21
/
Youtube3kTTSModel

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Mohsen21 commited on
Commit
a24bd60
•
1 Parent(s): f46ebb3

End of training

Browse files
Files changed (3) hide show
  1. README.md +111 -0
  2. generation_config.json +4 -0
  3. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,111 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ license: mit
4
+ base_model: microsoft/speecht5_tts
5
+ tags:
6
+ - generated_from_trainer
7
+ model-index:
8
+ - name: Youtube3kTTSModel
9
+ results: []
10
+ ---
11
+
12
+ <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
+ should probably proofread and complete it, then remove this comment. -->
14
+
15
+ # Youtube3kTTSModel
16
+
17
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4839
20
+
21
+ ## Model description
22
+
23
+ More information needed
24
+
25
+ ## Intended uses & limitations
26
+
27
+ More information needed
28
+
29
+ ## Training and evaluation data
30
+
31
+ More information needed
32
+
33
+ ## Training procedure
34
+
35
+ ### Training hyperparameters
36
+
37
+ The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 2
41
+ - seed: 42
42
+ - gradient_accumulation_steps: 8
43
+ - total_train_batch_size: 32
44
+ - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 100
47
+ - training_steps: 5000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.6301 | 0.2222 | 100 | 0.5639 |
55
+ | 0.6013 | 0.4444 | 200 | 0.5471 |
56
+ | 0.5666 | 0.6667 | 300 | 0.5315 |
57
+ | 0.5632 | 0.8889 | 400 | 0.5254 |
58
+ | 0.5547 | 1.1111 | 500 | 0.5184 |
59
+ | 0.5583 | 1.3333 | 600 | 0.5211 |
60
+ | 0.5527 | 1.5556 | 700 | 0.5150 |
61
+ | 0.5508 | 1.7778 | 800 | 0.5123 |
62
+ | 0.5432 | 2.0 | 900 | 0.5135 |
63
+ | 0.5478 | 2.2222 | 1000 | 0.5077 |
64
+ | 0.5419 | 2.4444 | 1100 | 0.5073 |
65
+ | 0.5439 | 2.6667 | 1200 | 0.5083 |
66
+ | 0.5381 | 2.8889 | 1300 | 0.5108 |
67
+ | 0.5355 | 3.1111 | 1400 | 0.5075 |
68
+ | 0.5317 | 3.3333 | 1500 | 0.5053 |
69
+ | 0.5345 | 3.5556 | 1600 | 0.5022 |
70
+ | 0.5329 | 3.7778 | 1700 | 0.5006 |
71
+ | 0.53 | 4.0 | 1800 | 0.4965 |
72
+ | 0.5261 | 4.2222 | 1900 | 0.4971 |
73
+ | 0.5272 | 4.4444 | 2000 | 0.4976 |
74
+ | 0.5272 | 4.6667 | 2100 | 0.4943 |
75
+ | 0.5282 | 4.8889 | 2200 | 0.4938 |
76
+ | 0.5188 | 5.1111 | 2300 | 0.4980 |
77
+ | 0.523 | 5.3333 | 2400 | 0.4894 |
78
+ | 0.5225 | 5.5556 | 2500 | 0.4915 |
79
+ | 0.5178 | 5.7778 | 2600 | 0.4960 |
80
+ | 0.5165 | 6.0 | 2700 | 0.4893 |
81
+ | 0.5098 | 6.2222 | 2800 | 0.4892 |
82
+ | 0.512 | 6.4444 | 2900 | 0.4868 |
83
+ | 0.5177 | 6.6667 | 3000 | 0.4868 |
84
+ | 0.5128 | 6.8889 | 3100 | 0.4883 |
85
+ | 0.5062 | 7.1111 | 3200 | 0.4852 |
86
+ | 0.5104 | 7.3333 | 3300 | 0.4898 |
87
+ | 0.5126 | 7.5556 | 3400 | 0.4887 |
88
+ | 0.5093 | 7.7778 | 3500 | 0.4908 |
89
+ | 0.5075 | 8.0 | 3600 | 0.4828 |
90
+ | 0.5029 | 8.2222 | 3700 | 0.4842 |
91
+ | 0.5079 | 8.4444 | 3800 | 0.4850 |
92
+ | 0.5049 | 8.6667 | 3900 | 0.4853 |
93
+ | 0.5034 | 8.8889 | 4000 | 0.4849 |
94
+ | 0.4984 | 9.1111 | 4100 | 0.4833 |
95
+ | 0.5079 | 9.3333 | 4200 | 0.4863 |
96
+ | 0.5023 | 9.5556 | 4300 | 0.4830 |
97
+ | 0.5023 | 9.7778 | 4400 | 0.4833 |
98
+ | 0.5037 | 10.0 | 4500 | 0.4825 |
99
+ | 0.5035 | 10.2222 | 4600 | 0.4822 |
100
+ | 0.5011 | 10.4444 | 4700 | 0.4826 |
101
+ | 0.4969 | 10.6667 | 4800 | 0.4815 |
102
+ | 0.4958 | 10.8889 | 4900 | 0.4839 |
103
+ | 0.4972 | 11.1111 | 5000 | 0.4839 |
104
+
105
+
106
+ ### Framework versions
107
+
108
+ - Transformers 4.44.2
109
+ - Pytorch 2.4.1+cu121
110
+ - Datasets 3.0.0
111
+ - Tokenizers 0.19.1
generation_config.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "max_length": 1876,
3
+ "transformers_version": "4.44.2"
4
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaa688958840d90c7cacb0007e4984456b884f4773204e1e5e291a6ad4e66d52
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da6211600e93d7b4ed6c951a7cb39ed9487d1736f976304365590458e2df855e
3
  size 577789320