Hugging Face's logo

ai557
/
speecht5_finetuned_nepali

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Model card Files
xet
Metrics Community
ai557 commited on
Commit
51658e4
·
verified ·
1 Parent(s): 9302142

End of training

Browse files
Files changed (4) hide show
  1. README.md +10 -22
  2. model.safetensors +1 -1
  3. runs/Jul07_09-39-00_hem-MS-7D88/events.out.tfevents.1751860442.hem-MS-7D88.11685.0 +3 -0
  4. training_args.bin +1 -1
README.md CHANGED
@@ -18,7 +18,7 @@ should probably proofread and complete it, then remove this comment. -->
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
20
  It achieves the following results on the evaluation set:
21
- - Loss: 1.1737
22
 
23
  ## Model description
24
 
@@ -37,38 +37,26 @@ More information needed
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
- - learning_rate: 5e-05
41
- - train_batch_size: 4
42
  - eval_batch_size: 8
43
  - seed: 42
44
- - gradient_accumulation_steps: 4
45
  - total_train_batch_size: 16
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
- - lr_scheduler_warmup_steps: 500
49
- - training_steps: 4000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
- | 0.1125 | 250.0 | 250 | 0.9197 |
57
- | 0.0907 | 500.0 | 500 | 1.0018 |
58
- | 0.0594 | 750.0 | 750 | 1.0658 |
59
- | 0.0779 | 1000.0 | 1000 | 1.0503 |
60
- | 0.0448 | 1250.0 | 1250 | 1.1411 |
61
- | 0.0391 | 1500.0 | 1500 | 1.1193 |
62
- | 0.0495 | 1750.0 | 1750 | 1.2151 |
63
- | 0.033 | 2000.0 | 2000 | 1.1058 |
64
- | 0.0338 | 2250.0 | 2250 | 1.1365 |
65
- | 0.0351 | 2500.0 | 2500 | 1.1647 |
66
- | 0.0334 | 2750.0 | 2750 | 1.1608 |
67
- | 0.0365 | 3000.0 | 3000 | 1.1428 |
68
- | 0.0338 | 3250.0 | 3250 | 1.1648 |
69
- | 0.0503 | 3500.0 | 3500 | 1.1689 |
70
- | 0.0311 | 3750.0 | 3750 | 1.1424 |
71
- | 0.0268 | 4000.0 | 4000 | 1.1737 |
72
 
73
 
74
  ### Framework versions
 
18
 
19
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the common_voice_11_0 dataset.
20
  It achieves the following results on the evaluation set:
21
+ - Loss: 1.2641
22
 
23
  ## Model description
24
 
 
37
  ### Training hyperparameters
38
 
39
  The following hyperparameters were used during training:
40
+ - learning_rate: 0.0001
41
+ - train_batch_size: 8
42
  - eval_batch_size: 8
43
  - seed: 42
44
+ - gradient_accumulation_steps: 2
45
  - total_train_batch_size: 16
46
  - optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
47
  - lr_scheduler_type: linear
48
+ - lr_scheduler_warmup_steps: 200
49
+ - training_steps: 2000
50
  - mixed_precision_training: Native AMP
51
 
52
  ### Training results
53
 
54
  | Training Loss | Epoch | Step | Validation Loss |
55
  |:-------------:|:------:|:----:|:---------------:|
56
+ | 0.1564 | 500.0 | 500 | 1.2493 |
57
+ | 0.0949 | 1000.0 | 1000 | 1.2334 |
58
+ | 0.0898 | 1500.0 | 1500 | 1.1982 |
59
+ | 0.0947 | 2000.0 | 2000 | 1.2641 |
 
 
 
 
 
 
 
 
 
 
 
 
60
 
61
 
62
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7e2084a2ef0eb133ef4c5a015eeca3c0734584d88d4ea12405472aa444e87d37
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de0912190e2f482ee0450989cbdf4799c0740b1d893a44a9676f13e47b4cdef6
3
  size 577789320
runs/Jul07_09-39-00_hem-MS-7D88/events.out.tfevents.1751860442.hem-MS-7D88.11685.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0cb6c168f88bf9cc737be74ce2f6eec7cf92affeddc8235ea168a9940c5aff64
3
+ size 24885
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5611f78e4392de3cce6386fc3ee95d2d17aef695825c2a9b554f31e78316678c
3
  size 5905
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7cf0c33a71a0cb755a7e6422fbdd347a9c1249b9e8bb6502c48ac2fc4c7e9e88
3
  size 5905