Hugging Face's logo

Strange18
/
speecht5_tts_voxpopuli_nl

Text-to-Audio
Transformers
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Community
Strange18 commited on
Commit
a900ed6
·
verified ·
1 Parent(s): e2cadea

End of training

Browse files
Files changed (3) hide show
  1. README.md +26 -16
  2. model.safetensors +1 -1
  3. training_args.bin +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: 0.4778
20
 
21
  ## Model description
22
 
@@ -36,31 +36,41 @@ More information needed
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 1e-05
39
- - train_batch_size: 8
40
  - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
- - total_train_batch_size: 16
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
- - training_steps: 1000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:-------:|:----:|:---------------:|
54
- | 0.8038 | 1.6667 | 100 | 0.6391 |
55
- | 0.6675 | 3.3333 | 200 | 0.5444 |
56
- | 0.5955 | 5.0 | 300 | 0.5115 |
57
- | 0.5658 | 6.6667 | 400 | 0.4928 |
58
- | 0.553 | 8.3333 | 500 | 0.4870 |
59
- | 0.5308 | 10.0 | 600 | 0.4822 |
60
- | 0.5262 | 11.6667 | 700 | 0.4806 |
61
- | 0.5405 | 13.3333 | 800 | 0.4791 |
62
- | 0.5267 | 15.0 | 900 | 0.4791 |
63
- | 0.525 | 16.6667 | 1000 | 0.4778 |
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### 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: 0.4761
20
 
21
  ## Model description
22
 
 
36
 
37
  The following hyperparameters were used during training:
38
  - learning_rate: 1e-05
39
+ - train_batch_size: 2
40
  - eval_batch_size: 2
41
  - seed: 42
42
  - gradient_accumulation_steps: 2
43
+ - total_train_batch_size: 4
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
+ | 0.6506 | 1.0 | 239 | 0.5907 |
55
+ | 0.5796 | 2.0 | 478 | 0.5158 |
56
+ | 0.5326 | 3.0 | 717 | 0.5087 |
57
+ | 0.5343 | 4.0 | 956 | 0.5023 |
58
+ | 0.5319 | 5.0 | 1195 | 0.4958 |
59
+ | 0.5193 | 6.0 | 1434 | 0.4878 |
60
+ | 0.5253 | 7.0 | 1673 | 0.4854 |
61
+ | 0.4992 | 8.0 | 1912 | 0.4851 |
62
+ | 0.4983 | 9.0 | 2151 | 0.4807 |
63
+ | 0.5039 | 10.0 | 2390 | 0.4781 |
64
+ | 0.5153 | 11.0 | 2629 | 0.4777 |
65
+ | 0.4882 | 12.0 | 2868 | 0.4773 |
66
+ | 0.4917 | 13.0 | 3107 | 0.4819 |
67
+ | 0.4942 | 14.0 | 3346 | 0.4758 |
68
+ | 0.4817 | 15.0 | 3585 | 0.4771 |
69
+ | 0.4832 | 16.0 | 3824 | 0.4763 |
70
+ | 0.4721 | 17.0 | 4063 | 0.4776 |
71
+ | 0.4975 | 18.0 | 4302 | 0.4789 |
72
+ | 0.493 | 19.0 | 4541 | 0.4770 |
73
+ | 0.4955 | 20.0 | 4780 | 0.4761 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:21ffa181920ec10e501e0a123ffc7b69a69c2d592fc37d510a260afce8515ca5
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3e3ff9388801dab67171b0abd3a20f0b92801b86c95508b47950142fdf31d139
3
  size 577789320
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19797838aaf06cc9da30259249fa2be87f4ceea75b94044a4585465d0a5b2aa5
3
  size 5496
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cb821b1350ad649ef6c37dceeb86c9879ecbaa36edbb899e3fc7e25fd00f5eb2
3
  size 5496