Hugging Face's logo

tdnathmlenthusiast
/
speecht5_finetuned_voice_dataset_bn_v_3

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
tdnathmlenthusiast commited on
Commit
29b8aca
·
verified ·
1 Parent(s): 5f37af9

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -6
  2. model.safetensors +1 -1
  3. runs/Oct20_14-52-54_1de5a974f526/events.out.tfevents.1729436115.1de5a974f526.1369.0 +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: 0.4129
20
 
21
  ## Model description
22
 
@@ -44,17 +44,25 @@ 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: 125
47
- - training_steps: 1000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:--------:|:----:|:---------------:|
54
- | 0.5225 | 28.5714 | 250 | 0.4591 |
55
- | 0.4792 | 57.1429 | 500 | 0.4299 |
56
- | 0.4638 | 85.7143 | 750 | 0.4171 |
57
- | 0.4593 | 114.2857 | 1000 | 0.4129 |
 
 
 
 
 
 
 
 
58
 
59
 
60
  ### Framework versions
 
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: 0.5008
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: 125
47
+ - training_steps: 3000
48
  - mixed_precision_training: Native AMP
49
 
50
  ### Training results
51
 
52
  | Training Loss | Epoch | Step | Validation Loss |
53
  |:-------------:|:--------:|:----:|:---------------:|
54
+ | 0.6046 | 12.2699 | 250 | 0.5646 |
55
+ | 0.5583 | 24.5399 | 500 | 0.5268 |
56
+ | 0.5364 | 36.8098 | 750 | 0.5188 |
57
+ | 0.5171 | 49.0798 | 1000 | 0.5087 |
58
+ | 0.5098 | 61.3497 | 1250 | 0.5018 |
59
+ | 0.501 | 73.6196 | 1500 | 0.5022 |
60
+ | 0.4984 | 85.8896 | 1750 | 0.4955 |
61
+ | 0.4929 | 98.1595 | 2000 | 0.5000 |
62
+ | 0.4933 | 110.4294 | 2250 | 0.4944 |
63
+ | 0.4868 | 122.6994 | 2500 | 0.5006 |
64
+ | 0.4805 | 134.9693 | 2750 | 0.4991 |
65
+ | 0.4802 | 147.2393 | 3000 | 0.5008 |
66
 
67
 
68
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:db7cb53aa427f6783f7892541b3c8328eb423a6f1005a4ad0c9824cfef48b04b
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:33f26c8a65e4237182c4096054ee9f7e0ca822ada5842e19f33cd6f2ce901bb3
3
  size 577789320
runs/Oct20_14-52-54_1de5a974f526/events.out.tfevents.1729436115.1de5a974f526.1369.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2871e55c8b95fa727ea4ed2c4691e50fc690ab0b20c024a89576f4c7b3397865
3
- size 35156
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6694f004d68a5ee5145f5d4f3c95817e720f5e5be4494f12cf52b069e8fc5d95
3
+ size 35510