Hugging Face's logo

kavinda123321
/
speecht5_kavinda1

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Metrics Community
kavinda123321 commited on
Commit
9fb49e3
·
verified ·
1 Parent(s): 8071254

End of training

Browse files
Files changed (3) hide show
  1. README.md +42 -22
  2. model.safetensors +1 -1
  3. runs/Jul09_07-37-29_49a083e747f2/events.out.tfevents.1752046656.49a083e747f2.757.0 +2 -2
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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4082
20
 
21
  ## Model description
22
 
@@ -44,33 +44,53 @@ The following hyperparameters were used during training:
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
47
- - num_epochs: 20
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
- | 0.37 | 1.0 | 14 | 0.3857 |
55
- | 0.3629 | 2.0 | 28 | 0.3915 |
56
- | 0.3673 | 3.0 | 42 | 0.3833 |
57
- | 0.3711 | 4.0 | 56 | 0.3847 |
58
- | 0.3632 | 5.0 | 70 | 0.3959 |
59
- | 0.3683 | 6.0 | 84 | 0.3900 |
60
- | 0.3692 | 7.0 | 98 | 0.4002 |
61
- | 0.3695 | 8.0 | 112 | 0.3855 |
62
- | 0.3767 | 9.0 | 126 | 0.3991 |
63
- | 0.3743 | 10.0 | 140 | 0.3919 |
64
- | 0.3615 | 11.0 | 154 | 0.4060 |
65
- | 0.3609 | 12.0 | 168 | 0.3962 |
66
- | 0.3534 | 13.0 | 182 | 0.3961 |
67
- | 0.3609 | 14.0 | 196 | 0.4191 |
68
- | 0.3639 | 15.0 | 210 | 0.3899 |
69
- | 0.3505 | 16.0 | 224 | 0.3951 |
70
- | 0.3464 | 17.0 | 238 | 0.4116 |
71
- | 0.341 | 18.0 | 252 | 0.4113 |
72
- | 0.3411 | 19.0 | 266 | 0.4066 |
73
- | 0.3439 | 20.0 | 280 | 0.4082 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.4020
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Use OptimizerNames.ADAMW_TORCH 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: 100
47
+ - num_epochs: 40
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-----:|:----:|:---------------:|
54
+ | 0.8309 | 1.0 | 14 | 0.5929 |
55
+ | 0.6544 | 2.0 | 28 | 0.5246 |
56
+ | 0.6079 | 3.0 | 42 | 0.4954 |
57
+ | 0.5618 | 4.0 | 56 | 0.4706 |
58
+ | 0.4976 | 5.0 | 70 | 0.4192 |
59
+ | 0.4688 | 6.0 | 84 | 0.4151 |
60
+ | 0.4628 | 7.0 | 98 | 0.4090 |
61
+ | 0.4365 | 8.0 | 112 | 0.4050 |
62
+ | 0.4674 | 9.0 | 126 | 0.4146 |
63
+ | 0.4548 | 10.0 | 140 | 0.3966 |
64
+ | 0.426 | 11.0 | 154 | 0.4067 |
65
+ | 0.4211 | 12.0 | 168 | 0.3890 |
66
+ | 0.4106 | 13.0 | 182 | 0.3842 |
67
+ | 0.4125 | 14.0 | 196 | 0.3863 |
68
+ | 0.4079 | 15.0 | 210 | 0.3810 |
69
+ | 0.4003 | 16.0 | 224 | 0.3731 |
70
+ | 0.396 | 17.0 | 238 | 0.3912 |
71
+ | 0.392 | 18.0 | 252 | 0.3810 |
72
+ | 0.387 | 19.0 | 266 | 0.3835 |
73
+ | 0.3908 | 20.0 | 280 | 0.3847 |
74
+ | 0.3846 | 21.0 | 294 | 0.3785 |
75
+ | 0.3834 | 22.0 | 308 | 0.3706 |
76
+ | 0.386 | 23.0 | 322 | 0.3826 |
77
+ | 0.3868 | 24.0 | 336 | 0.3899 |
78
+ | 0.3814 | 25.0 | 350 | 0.3859 |
79
+ | 0.3711 | 26.0 | 364 | 0.3980 |
80
+ | 0.3743 | 27.0 | 378 | 0.3855 |
81
+ | 0.3702 | 28.0 | 392 | 0.3896 |
82
+ | 0.3682 | 29.0 | 406 | 0.3976 |
83
+ | 0.3704 | 30.0 | 420 | 0.3898 |
84
+ | 0.3633 | 31.0 | 434 | 0.3868 |
85
+ | 0.364 | 32.0 | 448 | 0.3934 |
86
+ | 0.3674 | 33.0 | 462 | 0.3838 |
87
+ | 0.357 | 34.0 | 476 | 0.3909 |
88
+ | 0.3581 | 35.0 | 490 | 0.4014 |
89
+ | 0.3554 | 36.0 | 504 | 0.3981 |
90
+ | 0.361 | 37.0 | 518 | 0.3970 |
91
+ | 0.3531 | 38.0 | 532 | 0.3970 |
92
+ | 0.3486 | 39.0 | 546 | 0.3998 |
93
+ | 0.3499 | 40.0 | 560 | 0.4020 |
94
 
95
 
96
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:aaec647d41b12b09a2d6fabb8d59cc8b55cc71dd4c4d8fd0b61cd893d93beb09
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3b5730953238ba48756900beb5adbb55acac90f73949b949dccd69007d867218
3
  size 577789320
runs/Jul09_07-37-29_49a083e747f2/events.out.tfevents.1752046656.49a083e747f2.757.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1d05440a2e062776ec9427eff922a8462a8d40234c86472074ccb81eb8459902
3
- size 25305
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:914067318cf8ebc7c116788cfa5f63dd8f80d05bc8170efd504ef02a7cddfc62
3
+ size 26141