woodwardmw commited on
Commit
31caa4a
·
verified ·
1 Parent(s): 294a8e3

Model save

Browse files
Files changed (2) hide show
  1. README.md +101 -0
  2. model.safetensors +1 -1
README.md ADDED
@@ -0,0 +1,101 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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: iou-chapter-audio-dataset-force-aligned-speecht5
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
+ # iou-chapter-audio-dataset-force-aligned-speecht5
16
+
17
+ This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
18
+ It achieves the following results on the evaluation set:
19
+ - Loss: 0.4800
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: 8
40
+ - eval_batch_size: 8
41
+ - seed: 3407
42
+ - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 32
44
+ - optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
45
+ - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 4000
47
+ - training_steps: 40000
48
+ - mixed_precision_training: Native AMP
49
+
50
+ ### Training results
51
+
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:--------:|:-----:|:---------------:|
54
+ | 0.5387 | 5.2918 | 1000 | 0.5152 |
55
+ | 0.493 | 10.5836 | 2000 | 0.4955 |
56
+ | 0.4935 | 15.8753 | 3000 | 0.4885 |
57
+ | 0.4846 | 21.1645 | 4000 | 0.4863 |
58
+ | 0.4717 | 26.4562 | 5000 | 0.4825 |
59
+ | 0.4532 | 31.7480 | 6000 | 0.4804 |
60
+ | 0.4841 | 37.0371 | 7000 | 0.4802 |
61
+ | 0.458 | 42.3289 | 8000 | 0.4791 |
62
+ | 0.4454 | 47.6207 | 9000 | 0.4822 |
63
+ | 0.4461 | 52.9125 | 10000 | 0.4790 |
64
+ | 0.4362 | 58.2016 | 11000 | 0.4789 |
65
+ | 0.4301 | 63.4934 | 12000 | 0.4789 |
66
+ | 0.43 | 68.7851 | 13000 | 0.4806 |
67
+ | 0.4392 | 74.0743 | 14000 | 0.4796 |
68
+ | 0.4355 | 79.3660 | 15000 | 0.4797 |
69
+ | 0.4273 | 84.6578 | 16000 | 0.4778 |
70
+ | 0.4324 | 89.9496 | 17000 | 0.4808 |
71
+ | 0.4239 | 95.2387 | 18000 | 0.4792 |
72
+ | 0.4174 | 100.5305 | 19000 | 0.4786 |
73
+ | 0.4206 | 105.8223 | 20000 | 0.4777 |
74
+ | 0.4104 | 111.1114 | 21000 | 0.4784 |
75
+ | 0.4121 | 116.4032 | 22000 | 0.4797 |
76
+ | 0.4087 | 121.6950 | 23000 | 0.4800 |
77
+ | 0.4115 | 126.9867 | 24000 | 0.4788 |
78
+ | 0.405 | 132.2759 | 25000 | 0.4799 |
79
+ | 0.4091 | 137.5676 | 26000 | 0.4795 |
80
+ | 0.4165 | 142.8594 | 27000 | 0.4799 |
81
+ | 0.4059 | 148.1485 | 28000 | 0.4792 |
82
+ | 0.4092 | 153.4403 | 29000 | 0.4797 |
83
+ | 0.4006 | 158.7321 | 30000 | 0.4791 |
84
+ | 0.4033 | 164.0212 | 31000 | 0.4789 |
85
+ | 0.3929 | 169.3130 | 32000 | 0.4796 |
86
+ | 0.4024 | 174.6048 | 33000 | 0.4803 |
87
+ | 0.3988 | 179.8966 | 34000 | 0.4785 |
88
+ | 0.3965 | 185.1857 | 35000 | 0.4792 |
89
+ | 0.3914 | 190.4775 | 36000 | 0.4795 |
90
+ | 0.3967 | 195.7692 | 37000 | 0.4811 |
91
+ | 0.3994 | 201.0584 | 38000 | 0.4800 |
92
+ | 0.4019 | 206.3501 | 39000 | 0.4805 |
93
+ | 0.4005 | 211.6419 | 40000 | 0.4800 |
94
+
95
+
96
+ ### Framework versions
97
+
98
+ - Transformers 4.57.1
99
+ - Pytorch 2.8.0+cu128
100
+ - Datasets 4.2.0
101
+ - Tokenizers 0.22.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ac828fd755fa46a1d51cf108e5ad47e30c8a27f2735577982594f939b21bd2b5
3
  size 577847688
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6286c26db8a3551740aa9778760072519b99115f3b9e516735ebd973af45a9d0
3
  size 577847688