Hugging Face's logo

mikhail-panzo
/
fil_b32_le5_s4000

Text-to-Audio
Transformers
TensorBoard
Safetensors
speecht5
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
mikhail-panzo commited on
Commit
5013402
•
1 Parent(s): dad2128

End of training

Browse files
Files changed (2) hide show
  1. README.md +13 -13
  2. model.safetensors +1 -1
README.md CHANGED
@@ -15,7 +15,7 @@ should probably proofread and complete it, then remove this comment. -->
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
- - Loss: 0.4139
19
 
20
  ## Model description
21
 
@@ -38,8 +38,8 @@ The following hyperparameters were used during training:
38
  - train_batch_size: 16
39
  - eval_batch_size: 8
40
  - seed: 42
41
- - gradient_accumulation_steps: 2
42
- - total_train_batch_size: 32
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 2000
@@ -48,16 +48,16 @@ The following hyperparameters were used during training:
48
 
49
  ### Training results
50
 
51
- | Training Loss | Epoch | Step | Validation Loss |
52
- |:-------------:|:-------:|:----:|:---------------:|
53
- | 0.6246 | 11.1111 | 500 | 0.5376 |
54
- | 0.5034 | 22.2222 | 1000 | 0.4566 |
55
- | 0.4807 | 33.3333 | 1500 | 0.4360 |
56
- | 0.4582 | 44.4444 | 2000 | 0.4245 |
57
- | 0.4541 | 55.5556 | 2500 | 0.4213 |
58
- | 0.4409 | 66.6667 | 3000 | 0.4158 |
59
- | 0.4469 | 77.7778 | 3500 | 0.4153 |
60
- | 0.4337 | 88.8889 | 4000 | 0.4139 |
61
 
62
 
63
  ### Framework versions
 
15
 
16
  This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on an unknown dataset.
17
  It achieves the following results on the evaluation set:
18
+ - Loss: 0.4102
19
 
20
  ## Model description
21
 
 
38
  - train_batch_size: 16
39
  - eval_batch_size: 8
40
  - seed: 42
41
+ - gradient_accumulation_steps: 8
42
+ - total_train_batch_size: 128
43
  - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
44
  - lr_scheduler_type: linear
45
  - lr_scheduler_warmup_steps: 2000
 
48
 
49
  ### Training results
50
 
51
+ | Training Loss | Epoch | Step | Validation Loss |
52
+ |:-------------:|:--------:|:----:|:---------------:|
53
+ | 0.5539 | 44.4444 | 500 | 0.4850 |
54
+ | 0.4867 | 88.8889 | 1000 | 0.4439 |
55
+ | 0.4595 | 133.3333 | 1500 | 0.4245 |
56
+ | 0.4395 | 177.7778 | 2000 | 0.4155 |
57
+ | 0.4327 | 222.2222 | 2500 | 0.4121 |
58
+ | 0.4279 | 266.6667 | 3000 | 0.4127 |
59
+ | 0.4202 | 311.1111 | 3500 | 0.4098 |
60
+ | 0.4167 | 355.5556 | 4000 | 0.4102 |
61
 
62
 
63
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:20cd2f6fd31150b2d8bf831562c04ad14a54c8e1c9d8e4057c9f30c6ad1fc179
3
  size 577789320
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c824d19aa5d1fcd5db2eb32635530c0802a5445d7b4df95e9034779413bc0b0f
3
  size 577789320