Hugging Face's logo

woodwardmw
/
phase2

Text-to-Audio
Transformers
Safetensors
speecht5
Generated from Trainer
Model card Files Community
woodwardmw commited on
Commit
25dc1d8
·
verified ·
1 Parent(s): c47fc24

Model save

Browse files
Files changed (2) hide show
  1. README.md +26 -26
  2. model.safetensors +1 -1
README.md CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
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: 0.4742
20
 
21
  ## Model description
22
 
@@ -36,11 +36,11 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
- - train_batch_size: 16
40
- - eval_batch_size: 16
41
  - seed: 3407
42
  - gradient_accumulation_steps: 4
43
- - total_train_batch_size: 64
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: 50
@@ -49,28 +49,28 @@ The following hyperparameters were used during training:
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:--------:|:-----:|:---------------:|
54
- | 0.6082 | 10.6434 | 1000 | 0.5512 |
55
- | 0.4894 | 21.2788 | 2000 | 0.4854 |
56
- | 0.4848 | 31.9223 | 3000 | 0.4715 |
57
- | 0.4699 | 42.5576 | 4000 | 0.4692 |
58
- | 0.4505 | 53.1930 | 5000 | 0.4660 |
59
- | 0.4833 | 63.8365 | 6000 | 0.4602 |
60
- | 0.4277 | 74.4718 | 7000 | 0.4590 |
61
- | 0.4456 | 85.1072 | 8000 | 0.4689 |
62
- | 0.4086 | 95.7507 | 9000 | 0.4614 |
63
- | 0.4132 | 106.3861 | 10000 | 0.4654 |
64
- | 0.4083 | 117.0214 | 11000 | 0.4689 |
65
- | 0.4009 | 127.6649 | 12000 | 0.4672 |
66
- | 0.4556 | 138.3003 | 13000 | 0.4718 |
67
- | 0.3999 | 148.9437 | 14000 | 0.4684 |
68
- | 0.3988 | 159.5791 | 15000 | 0.4694 |
69
- | 0.3786 | 170.2145 | 16000 | 0.4711 |
70
- | 0.4181 | 180.8579 | 17000 | 0.4744 |
71
- | 0.3893 | 191.4933 | 18000 | 0.4747 |
72
- | 0.3694 | 202.1287 | 19000 | 0.4734 |
73
- | 0.3885 | 212.7721 | 20000 | 0.4742 |
74
 
75
 
76
  ### Framework versions
 
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: 0.4544
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 5e-05
39
+ - train_batch_size: 4
40
+ - eval_batch_size: 4
41
  - seed: 3407
42
  - gradient_accumulation_steps: 4
43
+ - total_train_batch_size: 16
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: 50
 
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:-----:|:---------------:|
54
+ | 0.5917 | 2.6823 | 1000 | 0.5957 |
55
+ | 0.5782 | 5.3627 | 2000 | 0.5542 |
56
+ | 0.5593 | 8.0430 | 3000 | 0.5318 |
57
+ | 0.4973 | 10.7253 | 4000 | 0.4915 |
58
+ | 0.4883 | 13.4056 | 5000 | 0.4819 |
59
+ | 0.4868 | 16.0860 | 6000 | 0.4706 |
60
+ | 0.5138 | 18.7683 | 7000 | 0.4689 |
61
+ | 0.4571 | 21.4486 | 8000 | 0.4650 |
62
+ | 0.4557 | 24.1289 | 9000 | 0.4675 |
63
+ | 0.5072 | 26.8113 | 10000 | 0.4631 |
64
+ | 0.492 | 29.4916 | 11000 | 0.4604 |
65
+ | 0.4535 | 32.1719 | 12000 | 0.4581 |
66
+ | 0.4668 | 34.8543 | 13000 | 0.4550 |
67
+ | 0.4825 | 37.5346 | 14000 | 0.4593 |
68
+ | 0.4551 | 40.2149 | 15000 | 0.4568 |
69
+ | 0.4285 | 42.8972 | 16000 | 0.4554 |
70
+ | 0.4383 | 45.5776 | 17000 | 0.4544 |
71
+ | 0.393 | 48.2579 | 18000 | 0.4529 |
72
+ | 0.4406 | 50.9402 | 19000 | 0.4570 |
73
+ | 0.4519 | 53.6206 | 20000 | 0.4544 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f8ea0cd6347affa6b4805adb3cfdc9df4553d232e990589dc5015b8d65a33881
3
  size 577976712
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e616c592d03dce5c2fa2aed2ba7a13dbcefd63c79a269470500eabaa3f419437
3
  size 577976712