End of training
Browse files
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 the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
-
- Loss: 0.
|
19 |
|
20 |
## Model description
|
21 |
|
@@ -35,26 +35,31 @@ More information needed
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1e-05
|
38 |
-
- train_batch_size:
|
39 |
- eval_batch_size: 2
|
40 |
- seed: 42
|
41 |
-
- gradient_accumulation_steps:
|
42 |
-
- total_train_batch_size:
|
43 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
44 |
- lr_scheduler_type: linear
|
45 |
-
- lr_scheduler_warmup_steps:
|
46 |
-
- training_steps:
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
-
| 0.
|
54 |
-
| 0.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
15 |
|
16 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the None dataset.
|
17 |
It achieves the following results on the evaluation set:
|
18 |
+
- Loss: 0.5067
|
19 |
|
20 |
## Model description
|
21 |
|
|
|
35 |
|
36 |
The following hyperparameters were used during training:
|
37 |
- learning_rate: 1e-05
|
38 |
+
- train_batch_size: 2
|
39 |
- eval_batch_size: 2
|
40 |
- seed: 42
|
41 |
+
- gradient_accumulation_steps: 16
|
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: 200
|
46 |
+
- training_steps: 1000
|
47 |
- mixed_precision_training: Native AMP
|
48 |
|
49 |
### Training results
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|
|
53 |
+
| 0.7136 | 0.03 | 100 | 0.6539 |
|
54 |
+
| 0.6471 | 0.06 | 200 | 0.5934 |
|
55 |
+
| 0.5851 | 0.08 | 300 | 0.5392 |
|
56 |
+
| 0.5764 | 0.11 | 400 | 0.5275 |
|
57 |
+
| 0.5666 | 0.14 | 500 | 0.5213 |
|
58 |
+
| 0.5577 | 0.17 | 600 | 0.5138 |
|
59 |
+
| 0.5605 | 0.2 | 700 | 0.5115 |
|
60 |
+
| 0.5622 | 0.22 | 800 | 0.5088 |
|
61 |
+
| 0.5603 | 0.25 | 900 | 0.5082 |
|
62 |
+
| 0.558 | 0.28 | 1000 | 0.5067 |
|
63 |
|
64 |
|
65 |
### Framework versions
|