Hugging Face's logo

Devishri1
/
finetuned_speecht5_50Kdata

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
Devishri1 commited on
Commit
89cd82e
•
1 Parent(s): 8c12be9

End of training

Browse files
Files changed (3) hide show
  1. README.md +17 -12
  2. model.safetensors +1 -1
  3. runs/Oct24_13-53-52_6a4782454a21/events.out.tfevents.1729784208.6a4782454a21.25154.1 +3 -0
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 the None dataset.
18
  It achieves the following results on the evaluation set:
19
- - Loss: 0.4724
20
 
21
  ## Model description
22
 
@@ -35,27 +35,32 @@ More information needed
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
- - learning_rate: 0.0001
39
- - train_batch_size: 4
40
- - eval_batch_size: 2
41
  - seed: 42
42
- - gradient_accumulation_steps: 8
43
  - total_train_batch_size: 32
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: 500
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
- | 0.6083 | 0.7011 | 100 | 0.5589 |
55
- | 0.5356 | 1.4023 | 200 | 0.5002 |
56
- | 0.5171 | 2.1034 | 300 | 0.4848 |
57
- | 0.4973 | 2.8046 | 400 | 0.4861 |
58
- | 0.4868 | 3.5057 | 500 | 0.4719 |
 
 
 
 
 
59
 
60
 
61
  ### Framework versions
 
16
 
17
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
18
  It achieves the following results on the evaluation set:
19
+ - Loss: 0.3766
20
 
21
  ## Model description
22
 
 
35
  ### Training hyperparameters
36
 
37
  The following hyperparameters were used during training:
38
+ - learning_rate: 3e-05
39
+ - train_batch_size: 16
40
+ - eval_batch_size: 8
41
  - seed: 42
42
+ - gradient_accumulation_steps: 2
43
  - total_train_batch_size: 32
44
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
45
  - lr_scheduler_type: linear
46
+ - lr_scheduler_warmup_steps: 500
47
+ - training_steps: 5000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:------:|:----:|:---------------:|
54
+ | 0.5055 | 0.3505 | 500 | 0.4585 |
55
+ | 0.4679 | 0.7010 | 1000 | 0.4248 |
56
+ | 0.4444 | 1.0515 | 1500 | 0.4140 |
57
+ | 0.4356 | 1.4020 | 2000 | 0.4109 |
58
+ | 0.434 | 1.7525 | 2500 | 0.4082 |
59
+ | 0.428 | 2.1030 | 3000 | 0.4023 |
60
+ | 0.423 | 2.4536 | 3500 | 0.4003 |
61
+ | 0.4177 | 2.8041 | 4000 | 0.3835 |
62
+ | 0.4077 | 3.1546 | 4500 | 0.3766 |
63
+ | 0.4096 | 3.5051 | 5000 | 0.3781 |
64
 
65
 
66
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d0e890673b8a78d776663f87dd1d7a26b36ea4e80469af93f9e55a3730816626
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba25db3ebcfa169f59f25d874101054876b724c73b2195b463f4989c5ae83916
3
  size 577789320
runs/Oct24_13-53-52_6a4782454a21/events.out.tfevents.1729784208.6a4782454a21.25154.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0cefd3095d56b36d36610619d7edf75849407b39da3b82128be9ce8582be48d
3
+ size 359