End of training
Browse files
README.md
CHANGED
@@ -17,8 +17,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Wer: 1.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -38,7 +38,7 @@ More information needed
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
-
- train_batch_size:
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
@@ -51,10 +51,20 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
-
|
|
55 |
-
|
|
56 |
-
| 6.
|
57 |
-
| 5.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
58 |
|
59 |
|
60 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/wav2vec2-base-960h](https://huggingface.co/facebook/wav2vec2-base-960h) on the None dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 4.7884
|
21 |
+
- Wer: 1.0
|
22 |
|
23 |
## Model description
|
24 |
|
|
|
38 |
|
39 |
The following hyperparameters were used during training:
|
40 |
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 8
|
42 |
- eval_batch_size: 8
|
43 |
- seed: 42
|
44 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
|
|
51 |
|
52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
54 |
+
| 8.6131 | 1.43 | 500 | 10.3380 | 1.0 |
|
55 |
+
| 7.3718 | 2.86 | 1000 | 8.0143 | 1.0 |
|
56 |
+
| 6.0492 | 4.29 | 1500 | 6.5868 | 1.0198 |
|
57 |
+
| 5.3856 | 5.71 | 2000 | 5.9299 | 1.0209 |
|
58 |
+
| 4.9947 | 7.14 | 2500 | 5.4516 | 1.0083 |
|
59 |
+
| 4.6977 | 8.57 | 3000 | 5.1176 | 1.0015 |
|
60 |
+
| 4.5413 | 10.0 | 3500 | 4.9814 | 1.0002 |
|
61 |
+
| 4.491 | 11.43 | 4000 | 4.9081 | 0.9999 |
|
62 |
+
| 4.4496 | 12.86 | 4500 | 4.8644 | 0.9999 |
|
63 |
+
| 4.4016 | 14.29 | 5000 | 4.8368 | 0.9999 |
|
64 |
+
| 4.3977 | 15.71 | 5500 | 4.8137 | 1.0 |
|
65 |
+
| 4.4179 | 17.14 | 6000 | 4.8038 | 1.0 |
|
66 |
+
| 4.3831 | 18.57 | 6500 | 4.7890 | 1.0 |
|
67 |
+
| 4.3699 | 20.0 | 7000 | 4.7884 | 1.0 |
|
68 |
|
69 |
|
70 |
### Framework versions
|