Hugging Face's logo

iqrabatool
/
Finetuned_speecht5

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
iqrabatool commited on
Commit
41a5ea1
•
1 Parent(s): f9b366f

End of training

Browse files
Files changed (3) hide show
  1. README.md +12 -12
  2. model.safetensors +1 -1
  3. runs/Jul27_09-05-36_09f0ec7a04b4/events.out.tfevents.1722071147.09f0ec7a04b4.34.0 +2 -2
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.4932
19
 
20
  ## Model description
21
 
@@ -43,23 +43,23 @@ The following hyperparameters were used during training:
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 500
46
- - training_steps: 1000
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-------:|:----:|:---------------:|
53
- | 0.8772 | 6.8966 | 100 | 0.7399 |
54
- | 0.8105 | 13.7931 | 200 | 0.6896 |
55
- | 0.6876 | 20.6897 | 300 | 0.5928 |
56
- | 0.5714 | 27.5862 | 400 | 0.5120 |
57
- | 0.5572 | 34.4828 | 500 | 0.4993 |
58
- | 0.539 | 41.3793 | 600 | 0.4985 |
59
- | 0.5276 | 48.2759 | 700 | 0.4917 |
60
- | 0.5219 | 55.1724 | 800 | 0.4915 |
61
- | 0.506 | 62.0690 | 900 | 0.4913 |
62
- | 0.51 | 68.9655 | 1000 | 0.4932 |
63
 
64
 
65
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.5028
19
 
20
  ## Model description
21
 
 
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 500
46
+ - training_steps: 5000
47
  - mixed_precision_training: Native AMP
48
 
49
  ### Training results
50
 
51
  | Training Loss | Epoch | Step | Validation Loss |
52
  |:-------------:|:-------:|:----:|:---------------:|
53
+ | 0.6106 | 8.8496 | 500 | 0.5241 |
54
+ | 0.5243 | 17.6991 | 1000 | 0.4949 |
55
+ | 0.5004 | 26.5487 | 1500 | 0.4873 |
56
+ | 0.4918 | 35.3982 | 2000 | 0.4871 |
57
+ | 0.4927 | 44.2478 | 2500 | 0.4922 |
58
+ | 0.4715 | 53.0973 | 3000 | 0.4964 |
59
+ | 0.4832 | 61.9469 | 3500 | 0.4996 |
60
+ | 0.4744 | 70.7965 | 4000 | 0.5028 |
61
+ | 0.4677 | 79.6460 | 4500 | 0.5046 |
62
+ | 0.4568 | 88.4956 | 5000 | 0.5028 |
63
 
64
 
65
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3ad66abf96832ffc974375f089ca3bb252382c487b6d2141be81e25431a6f59a
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5923b390e759c63cb734abf846f545081339c4f013c77d92ce37ef76cd819e60
3
  size 577789320
runs/Jul27_09-05-36_09f0ec7a04b4/events.out.tfevents.1722071147.09f0ec7a04b4.34.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:943bbbcfb89c6de2bb603a373031368dbb6c9a6a7baa16c69f095876e3b9a7e2
3
- size 51410
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bab3b7d9e7f42f569282e5115c6ac9e0c258f2c243a9472c57ed55f375cbd584
3
+ size 51764