Hugging Face's logo

fahadqazi
/
Sindhi-TTS

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
fahadqazi commited on
Commit
267862e
·
verified ·
1 Parent(s): 3ba8e97

End of training

Browse files
Files changed (2) hide show
  1. README.md +62 -4
  2. model.safetensors +1 -1
README.md CHANGED
@@ -1,7 +1,7 @@
1
  ---
2
  library_name: transformers
3
  license: mit
4
- base_model: fahadqazi/Sindhi-TTS
5
  tags:
6
  - generated_from_trainer
7
  model-index:
@@ -14,7 +14,9 @@ should probably proofread and complete it, then remove this comment. -->
14
 
15
  # Sindhi-TTS
16
 
17
- This model is a fine-tuned version of [fahadqazi/Sindhi-TTS](https://huggingface.co/fahadqazi/Sindhi-TTS) on the None dataset.
 
 
18
 
19
  ## Model description
20
 
@@ -33,9 +35,9 @@ More information needed
33
  ### Training hyperparameters
34
 
35
  The following hyperparameters were used during training:
36
- - learning_rate: 1e-05
37
  - train_batch_size: 16
38
- - eval_batch_size: 16
39
  - seed: 42
40
  - gradient_accumulation_steps: 4
41
  - total_train_batch_size: 64
@@ -45,6 +47,62 @@ The following hyperparameters were used during training:
45
  - training_steps: 5000
46
  - mixed_precision_training: Native AMP
47
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
48
  ### Framework versions
49
 
50
  - Transformers 4.46.2
 
1
  ---
2
  library_name: transformers
3
  license: mit
4
+ base_model: Sana1207/Hindi_SpeechT5_finetuned
5
  tags:
6
  - generated_from_trainer
7
  model-index:
 
14
 
15
  # Sindhi-TTS
16
 
17
+ This model is a fine-tuned version of [Sana1207/Hindi_SpeechT5_finetuned](https://huggingface.co/Sana1207/Hindi_SpeechT5_finetuned) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4887
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 0.0001
39
  - train_batch_size: 16
40
+ - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 4
43
  - total_train_batch_size: 64
 
47
  - training_steps: 5000
48
  - mixed_precision_training: Native AMP
49
 
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.5769 | 0.3992 | 100 | 0.5673 |
55
+ | 0.5602 | 0.7984 | 200 | 0.5603 |
56
+ | 0.553 | 1.1986 | 300 | 0.5489 |
57
+ | 0.5413 | 1.5978 | 400 | 0.5433 |
58
+ | 0.5361 | 1.9970 | 500 | 0.5336 |
59
+ | 0.5391 | 2.3972 | 600 | 0.5414 |
60
+ | 0.524 | 2.7964 | 700 | 0.5290 |
61
+ | 0.5253 | 3.1966 | 800 | 0.5317 |
62
+ | 0.5272 | 3.5958 | 900 | 0.5234 |
63
+ | 0.5258 | 3.9950 | 1000 | 0.5280 |
64
+ | 0.5173 | 4.3952 | 1100 | 0.5180 |
65
+ | 0.518 | 4.7944 | 1200 | 0.5207 |
66
+ | 0.5119 | 5.1946 | 1300 | 0.5157 |
67
+ | 0.5114 | 5.5938 | 1400 | 0.5169 |
68
+ | 0.5138 | 5.9930 | 1500 | 0.5140 |
69
+ | 0.5048 | 6.3932 | 1600 | 0.5122 |
70
+ | 0.5059 | 6.7924 | 1700 | 0.5173 |
71
+ | 0.4991 | 7.1926 | 1800 | 0.5057 |
72
+ | 0.5038 | 7.5918 | 1900 | 0.5053 |
73
+ | 0.4994 | 7.9910 | 2000 | 0.5071 |
74
+ | 0.4989 | 8.3912 | 2100 | 0.5080 |
75
+ | 0.4951 | 8.7904 | 2200 | 0.5099 |
76
+ | 0.4941 | 9.1906 | 2300 | 0.5022 |
77
+ | 0.493 | 9.5898 | 2400 | 0.5039 |
78
+ | 0.4915 | 9.9890 | 2500 | 0.5014 |
79
+ | 0.4911 | 10.3892 | 2600 | 0.5066 |
80
+ | 0.4861 | 10.7884 | 2700 | 0.4987 |
81
+ | 0.4875 | 11.1886 | 2800 | 0.5042 |
82
+ | 0.4892 | 11.5878 | 2900 | 0.4980 |
83
+ | 0.4909 | 11.9870 | 3000 | 0.5007 |
84
+ | 0.4886 | 12.3872 | 3100 | 0.4980 |
85
+ | 0.4857 | 12.7864 | 3200 | 0.4952 |
86
+ | 0.4868 | 13.1866 | 3300 | 0.4972 |
87
+ | 0.482 | 13.5858 | 3400 | 0.4957 |
88
+ | 0.479 | 13.9850 | 3500 | 0.5029 |
89
+ | 0.48 | 14.3852 | 3600 | 0.4954 |
90
+ | 0.4819 | 14.7844 | 3700 | 0.4982 |
91
+ | 0.4791 | 15.1846 | 3800 | 0.4936 |
92
+ | 0.4776 | 15.5838 | 3900 | 0.4947 |
93
+ | 0.4736 | 15.9830 | 4000 | 0.4930 |
94
+ | 0.4744 | 16.3832 | 4100 | 0.4937 |
95
+ | 0.4735 | 16.7824 | 4200 | 0.4895 |
96
+ | 0.4789 | 17.1826 | 4300 | 0.4936 |
97
+ | 0.4729 | 17.5818 | 4400 | 0.4920 |
98
+ | 0.4742 | 17.9810 | 4500 | 0.4915 |
99
+ | 0.4721 | 18.3812 | 4600 | 0.4887 |
100
+ | 0.4733 | 18.7804 | 4700 | 0.4933 |
101
+ | 0.4849 | 19.1806 | 4800 | 0.4879 |
102
+ | 0.4692 | 19.5798 | 4900 | 0.4889 |
103
+ | 0.4747 | 19.9790 | 5000 | 0.4887 |
104
+
105
+
106
  ### Framework versions
107
 
108
  - Transformers 4.46.2
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:314f115ee55ee4bce5faa1d21d90cb8ca876c99893b6b3fddbea3b2463a542e0
3
  size 617574792
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4a99ca78ee1943c295d70e9d84ae16e7b27a8e168616f231b17a325b77e804fb
3
  size 617574792