Hugging Face's logo

maghrane
/
speecht5_finetuned_Mar

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
maghrane commited on
Commit
58d7c36
·
verified ·
1 Parent(s): 76c97af

End of training

Browse files
Files changed (4) hide show
  1. README.md +33 -18
  2. generation_config.json +1 -1
  3. model.safetensors +1 -1
  4. runs/Dec06_10-30-42_043284d12555/events.out.tfevents.1733481044.043284d12555.413.0 +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 an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4845
20
 
21
  ## Model description
22
 
@@ -44,33 +44,48 @@ The following hyperparameters were used during training:
44
  - optimizer: Use 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: 50
47
- - training_steps: 1500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
- | 0.7023 | 0.7976 | 100 | 0.6419 |
55
- | 0.6105 | 1.5952 | 200 | 0.5699 |
56
- | 0.5895 | 2.3928 | 300 | 0.5631 |
57
- | 0.5796 | 3.1904 | 400 | 0.5530 |
58
- | 0.5818 | 3.9880 | 500 | 0.5388 |
59
- | 0.5448 | 4.7856 | 600 | 0.5399 |
60
- | 0.562 | 5.5833 | 700 | 0.5166 |
61
- | 0.542 | 6.3809 | 800 | 0.5207 |
62
- | 0.5374 | 7.1785 | 900 | 0.5118 |
63
- | 0.5263 | 7.9761 | 1000 | 0.5009 |
64
- | 0.5079 | 8.7737 | 1100 | 0.4965 |
65
- | 0.5108 | 9.5713 | 1200 | 0.4884 |
66
- | 0.497 | 10.3689 | 1300 | 0.4883 |
67
- | 0.4915 | 11.1665 | 1400 | 0.4896 |
68
- | 0.5061 | 11.9641 | 1500 | 0.4845 |
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
69
 
70
 
71
  ### Framework versions
72
 
73
- - Transformers 4.46.2
74
  - Pytorch 2.5.1+cu121
75
  - Datasets 3.1.0
76
  - Tokenizers 0.20.3
 
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: 0.4785
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Use 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: 50
47
+ - training_steps: 3000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.6818 | 0.7976 | 100 | 0.6565 |
55
+ | 0.6107 | 1.5952 | 200 | 0.5797 |
56
+ | 0.6033 | 2.3928 | 300 | 0.5716 |
57
+ | 0.5893 | 3.1904 | 400 | 0.5686 |
58
+ | 0.5919 | 3.9880 | 500 | 0.5624 |
59
+ | 0.5732 | 4.7856 | 600 | 0.5932 |
60
+ | 0.5677 | 5.5833 | 700 | 0.5485 |
61
+ | 0.5521 | 6.3809 | 800 | 0.5407 |
62
+ | 0.5513 | 7.1785 | 900 | 0.5348 |
63
+ | 0.5488 | 7.9761 | 1000 | 0.5366 |
64
+ | 0.5344 | 8.7737 | 1100 | 0.5267 |
65
+ | 0.5329 | 9.5713 | 1200 | 0.5163 |
66
+ | 0.5118 | 10.3689 | 1300 | 0.5172 |
67
+ | 0.5126 | 11.1665 | 1400 | 0.5089 |
68
+ | 0.5256 | 11.9641 | 1500 | 0.5104 |
69
+ | 0.5126 | 12.7617 | 1600 | 0.5054 |
70
+ | 0.5034 | 13.5593 | 1700 | 0.5023 |
71
+ | 0.4986 | 14.3569 | 1800 | 0.4974 |
72
+ | 0.4926 | 15.1545 | 1900 | 0.5081 |
73
+ | 0.4961 | 15.9521 | 2000 | 0.4929 |
74
+ | 0.4886 | 16.7498 | 2100 | 0.4863 |
75
+ | 0.491 | 17.5474 | 2200 | 0.4925 |
76
+ | 0.4845 | 18.3450 | 2300 | 0.4859 |
77
+ | 0.4726 | 19.1426 | 2400 | 0.4835 |
78
+ | 0.4786 | 19.9402 | 2500 | 0.4829 |
79
+ | 0.4732 | 20.7378 | 2600 | 0.4800 |
80
+ | 0.4713 | 21.5354 | 2700 | 0.4737 |
81
+ | 0.4571 | 22.3330 | 2800 | 0.4789 |
82
+ | 0.4559 | 23.1306 | 2900 | 0.4771 |
83
+ | 0.4552 | 23.9282 | 3000 | 0.4785 |
84
 
85
 
86
  ### Framework versions
87
 
88
+ - Transformers 4.46.3
89
  - Pytorch 2.5.1+cu121
90
  - Datasets 3.1.0
91
  - Tokenizers 0.20.3
generation_config.json CHANGED
@@ -5,5 +5,5 @@
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
- "transformers_version": "4.46.2"
9
  }
 
5
  "eos_token_id": 2,
6
  "max_length": 1876,
7
  "pad_token_id": 1,
8
+ "transformers_version": "4.46.3"
9
  }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b554041ae868e86cb82debec368f279fdd54c0c3c79973ece8f5355a3de0b4ce
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a4f8eefd626c510008b50ffd8999c3932f1d0a93dfe0689e7d8303cdfba7a37
3
  size 577789320
runs/Dec06_10-30-42_043284d12555/events.out.tfevents.1733481044.043284d12555.413.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8b06ddc07ee5deb3e849d7676f5b584c66ea83736429919d9edd296dd96c0f3e
3
- size 40118
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18e95f14d5b8621575517513416fd0f67f2fae8ec4025ef20253cb7aa09e81b4
3
+ size 40472