Hugging Face's logo

Kaizendsds
/
speecht5_arabic_female_voice

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
 Metrics Community
Kaizendsds commited on
Commit
fcb7dc8
·
verified ·
1 Parent(s): 0193a71

End of training

Browse files
Files changed (2) hide show
  1. README.md +14 -4
  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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.3886
20
 
21
  ## Model description
22
 
@@ -35,7 +35,7 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
  - train_batch_size: 4
40
  - eval_batch_size: 2
41
  - seed: 42
@@ -43,8 +43,8 @@ The following hyperparameters were used during training:
43
  - total_train_batch_size: 32
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: 200
47
- - training_steps: 2000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
@@ -61,6 +61,16 @@ The following hyperparameters were used during training:
61
  | 0.4011 | 34.6883 | 1600 | 0.3920 |
62
  | 0.3971 | 39.0244 | 1800 | 0.3905 |
63
  | 0.3898 | 43.3604 | 2000 | 0.3886 |
 
 
 
 
 
 
 
 
 
 
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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3636
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
  - train_batch_size: 4
40
  - eval_batch_size: 2
41
  - seed: 42
 
43
  - total_train_batch_size: 32
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: 400
47
+ - training_steps: 4000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
 
61
  | 0.4011 | 34.6883 | 1600 | 0.3920 |
62
  | 0.3971 | 39.0244 | 1800 | 0.3905 |
63
  | 0.3898 | 43.3604 | 2000 | 0.3886 |
64
+ | 0.3923 | 47.8130 | 2200 | 0.3813 |
65
+ | 0.3755 | 52.1491 | 2400 | 0.3691 |
66
+ | 0.3629 | 56.4851 | 2600 | 0.3655 |
67
+ | 0.3599 | 60.8211 | 2800 | 0.3660 |
68
+ | 0.3525 | 65.1572 | 3000 | 0.3632 |
69
+ | 0.3493 | 69.4932 | 3200 | 0.3603 |
70
+ | 0.3452 | 73.8293 | 3400 | 0.3626 |
71
+ | 0.3468 | 78.1653 | 3600 | 0.3597 |
72
+ | 0.3411 | 82.5014 | 3800 | 0.3621 |
73
+ | 0.3464 | 86.8374 | 4000 | 0.3636 |
74
 
75
 
76
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:51c80be979717e0436d49742a705164c04554dd6a297d3004f4cca9d8e007546
3
  size 577945992
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e78b81b4340f5048aec05a3481102c5b88f3d70feac9e9942eeda1bb9c77f628
3
  size 577945992