End of training
Browse files
README.md
CHANGED
@@ -17,7 +17,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -36,7 +36,7 @@ More information needed
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
-
- learning_rate: 1e-
|
40 |
- train_batch_size: 16
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
@@ -44,18 +44,24 @@ The following hyperparameters were used during training:
|
|
44 |
- total_train_batch_size: 32
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
-
- lr_scheduler_warmup_steps:
|
48 |
-
- training_steps:
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
-
| Training Loss | Epoch
|
54 |
-
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
59 |
|
60 |
|
61 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [microsoft/speecht5_tts](https://huggingface.co/microsoft/speecht5_tts) on the voxpopuli dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.6262
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
36 |
### Training hyperparameters
|
37 |
|
38 |
The following hyperparameters were used during training:
|
39 |
+
- learning_rate: 1e-06
|
40 |
- train_batch_size: 16
|
41 |
- eval_batch_size: 8
|
42 |
- seed: 42
|
|
|
44 |
- total_train_batch_size: 32
|
45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
46 |
- lr_scheduler_type: linear
|
47 |
+
- lr_scheduler_warmup_steps: 100
|
48 |
+
- training_steps: 1000
|
49 |
- mixed_precision_training: Native AMP
|
50 |
|
51 |
### Training results
|
52 |
|
53 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
54 |
+
|:-------------:|:------:|:----:|:---------------:|
|
55 |
+
| 0.7564 | 0.6116 | 100 | 0.7051 |
|
56 |
+
| 0.7636 | 1.2232 | 200 | 0.6764 |
|
57 |
+
| 0.7263 | 1.8349 | 300 | 0.6662 |
|
58 |
+
| 0.7262 | 2.4465 | 400 | 0.6555 |
|
59 |
+
| 0.7038 | 3.0581 | 500 | 0.6483 |
|
60 |
+
| 0.6931 | 3.6697 | 600 | 0.6422 |
|
61 |
+
| 0.6881 | 4.2813 | 700 | 0.6344 |
|
62 |
+
| 0.6916 | 4.8930 | 800 | 0.6300 |
|
63 |
+
| 0.6814 | 5.5046 | 900 | 0.6286 |
|
64 |
+
| 0.6692 | 6.1162 | 1000 | 0.6262 |
|
65 |
|
66 |
|
67 |
### Framework versions
|