Hugging Face's logo

CarmelaFinianos
/
ArabicTTS

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
CarmelaFinianos commited on
Commit
df16e5d
•
1 Parent(s): ca49ebb

End of training

Browse files
Files changed (3) hide show
  1. README.md +24 -20
  2. model.safetensors +1 -1
  3. runs/Nov20_15-37-40_03fbc943ea3b/events.out.tfevents.1732117091.03fbc943ea3b.591.0 +2 -2
README.md CHANGED
@@ -5,18 +5,18 @@ base_model: MBZUAI/speecht5_tts_clartts_ar
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
- - name: ArabicTTS
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
- # ArabicTTS
16
 
17
  This model is a fine-tuned version of [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.5655
20
 
21
  ## Model description
22
 
@@ -44,27 +44,31 @@ 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: 100
47
- - training_steps: 700
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
- | Training Loss | Epoch | Step | Validation Loss |
53
- |:-------------:|:--------:|:----:|:---------------:|
54
- | 0.6259 | 8.1509 | 50 | 0.6030 |
55
- | 0.5631 | 16.3019 | 100 | 0.5849 |
56
- | 0.5468 | 24.4528 | 150 | 0.5856 |
57
- | 0.5217 | 32.6038 | 200 | 0.5570 |
58
- | 0.5102 | 40.7547 | 250 | 0.5555 |
59
- | 0.4944 | 48.9057 | 300 | 0.5534 |
60
- | 0.4829 | 57.1321 | 350 | 0.5509 |
61
- | 0.477 | 65.2830 | 400 | 0.5567 |
62
- | 0.4692 | 73.4340 | 450 | 0.5552 |
63
- | 0.4635 | 81.5849 | 500 | 0.5572 |
64
- | 0.4592 | 89.7358 | 550 | 0.5573 |
65
- | 0.4546 | 97.8868 | 600 | 0.5610 |
66
- | 0.4515 | 106.1132 | 650 | 0.5653 |
67
- | 0.45 | 114.2642 | 700 | 0.5655 |
 
 
 
 
68
 
69
 
70
  ### Framework versions
 
5
  tags:
6
  - generated_from_trainer
7
  model-index:
8
+ - name: Arabictts
9
  results: []
10
  ---
11
 
12
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
13
  should probably proofread and complete it, then remove this comment. -->
14
 
15
+ # Arabictts
16
 
17
  This model is a fine-tuned version of [MBZUAI/speecht5_tts_clartts_ar](https://huggingface.co/MBZUAI/speecht5_tts_clartts_ar) on an unknown dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.5481
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: 100
47
+ - training_steps: 900
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
+ | Training Loss | Epoch | Step | Validation Loss |
53
+ |:-------------:|:-------:|:----:|:---------------:|
54
+ | 0.6582 | 3.7736 | 50 | 0.5892 |
55
+ | 0.603 | 7.5472 | 100 | 0.5603 |
56
+ | 0.5828 | 11.3208 | 150 | 0.5545 |
57
+ | 0.566 | 15.0943 | 200 | 0.5418 |
58
+ | 0.5504 | 18.8679 | 250 | 0.5393 |
59
+ | 0.5379 | 22.6415 | 300 | 0.5357 |
60
+ | 0.534 | 26.4151 | 350 | 0.5347 |
61
+ | 0.5226 | 30.1887 | 400 | 0.5352 |
62
+ | 0.5159 | 33.9623 | 450 | 0.5335 |
63
+ | 0.5058 | 37.7358 | 500 | 0.5350 |
64
+ | 0.5048 | 41.5094 | 550 | 0.5356 |
65
+ | 0.4994 | 45.2830 | 600 | 0.5367 |
66
+ | 0.4939 | 49.0566 | 650 | 0.5370 |
67
+ | 0.4923 | 52.8302 | 700 | 0.5366 |
68
+ | 0.488 | 56.6038 | 750 | 0.5397 |
69
+ | 0.4841 | 60.3774 | 800 | 0.5401 |
70
+ | 0.4834 | 64.1509 | 850 | 0.5490 |
71
+ | 0.4794 | 67.9245 | 900 | 0.5481 |
72
 
73
 
74
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d109638daa0f983501fad4f9d8a6978e81afde5f3b1aac2f3551b9b84dc58fd7
3
  size 577841544
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:080faa4aaa6c8aa31e670a512d3eca34fd787928bf56b88b02a0874f0a9f35a1
3
  size 577841544
runs/Nov20_15-37-40_03fbc943ea3b/events.out.tfevents.1732117091.03fbc943ea3b.591.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:c2d9682f9c8bca1e03d8afaf45b14c3b1f420c641ec49dcea7244a7863953c50
3
- size 19104
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:918d3b930c51bf10fddde353656dcab21f7b097f34e89fb8bbb8f9ced88e2a42
3
+ size 19458