Hugging Face's logo

Shabdobhedi
/
speecht5_finetuned_English_Technical_Shabdobhedii

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Shabdobhedi commited on
Commit
54f509a
·
verified ·
1 Parent(s): 0c44e6f

End of training

Browse files
Files changed (3) hide show
  1. README.md +13 -23
  2. model.safetensors +1 -1
  3. runs/Oct23_14-53-05_27d36d51f32a/events.out.tfevents.1729695229.27d36d51f32a.4298.0 +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: 0.4435
20
 
21
  ## Model description
22
 
@@ -44,38 +44,28 @@ The following hyperparameters were used during training:
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
  - lr_scheduler_warmup_steps: 100
47
- - training_steps: 2000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.5915 | 0.3581 | 100 | 0.5128 |
55
- | 0.5448 | 0.7162 | 200 | 0.4945 |
56
- | 0.5195 | 1.0743 | 300 | 0.4740 |
57
- | 0.5109 | 1.4324 | 400 | 0.4754 |
58
- | 0.5023 | 1.7905 | 500 | 0.4648 |
59
- | 0.4995 | 2.1486 | 600 | 0.4661 |
60
- | 0.4987 | 2.5067 | 700 | 0.4591 |
61
- | 0.4931 | 2.8648 | 800 | 0.4574 |
62
- | 0.4776 | 3.2229 | 900 | 0.4572 |
63
- | 0.4798 | 3.5810 | 1000 | 0.4516 |
64
- | 0.4786 | 3.9391 | 1100 | 0.4479 |
65
- | 0.4668 | 4.2972 | 1200 | 0.4504 |
66
- | 0.4714 | 4.6553 | 1300 | 0.4468 |
67
- | 0.4717 | 5.0134 | 1400 | 0.4463 |
68
- | 0.4662 | 5.3715 | 1500 | 0.4498 |
69
- | 0.4637 | 5.7296 | 1600 | 0.4461 |
70
- | 0.455 | 6.0877 | 1700 | 0.4474 |
71
- | 0.4551 | 6.4458 | 1800 | 0.4451 |
72
- | 0.462 | 6.8039 | 1900 | 0.4420 |
73
- | 0.4511 | 7.1620 | 2000 | 0.4435 |
74
 
75
 
76
  ### Framework versions
77
 
78
  - Transformers 4.44.2
79
  - Pytorch 2.4.1+cu121
80
- - Datasets 3.0.1
81
  - Tokenizers 0.19.1
 
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: 0.4481
20
 
21
  ## Model description
22
 
 
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
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
+ | 0.5889 | 0.3581 | 100 | 0.5117 |
55
+ | 0.5419 | 0.7162 | 200 | 0.4928 |
56
+ | 0.5203 | 1.0743 | 300 | 0.4762 |
57
+ | 0.5079 | 1.4324 | 400 | 0.4699 |
58
+ | 0.5022 | 1.7905 | 500 | 0.4580 |
59
+ | 0.4952 | 2.1486 | 600 | 0.4601 |
60
+ | 0.4886 | 2.5067 | 700 | 0.4579 |
61
+ | 0.4853 | 2.8648 | 800 | 0.4520 |
62
+ | 0.4762 | 3.2229 | 900 | 0.4477 |
63
+ | 0.4774 | 3.5810 | 1000 | 0.4481 |
 
 
 
 
 
 
 
 
 
 
64
 
65
 
66
  ### Framework versions
67
 
68
  - Transformers 4.44.2
69
  - Pytorch 2.4.1+cu121
70
+ - Datasets 3.0.2
71
  - Tokenizers 0.19.1
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91d3f8fbb5767fe70d05bee0518469d620d601c0090879e9c3e858b5b9cb7548
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:928ab5983d0ea71aecc7bf0f6882dc0a3548f584b56ac5236776fbd60d406f0e
3
  size 577789320
runs/Oct23_14-53-05_27d36d51f32a/events.out.tfevents.1729695229.27d36d51f32a.4298.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fe0d8306d549b6bb2c8576a95cae41924cf8d4ca1dc7c3df9634901366ab9467
3
- size 17799
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:04b86f118d8ac2effce1197a7fc67485e98b61422317044e5f6a3e7c484893e8
3
+ size 18153