update model card README.md
Browse files
README.md
CHANGED
@@ -17,12 +17,12 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss:
|
21 |
-
- Rouge1:
|
22 |
-
- Rouge2:
|
23 |
-
- Rougel:
|
24 |
-
- Rougelsum:
|
25 |
-
- Gen Len:
|
26 |
|
27 |
## Model description
|
28 |
|
@@ -51,13 +51,13 @@ The following hyperparameters were used during training:
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
-
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2
|
55 |
-
|
56 |
-
|
|
57 |
-
| 2.
|
58 |
-
| 1.
|
59 |
-
| 1.
|
60 |
-
| 1.
|
61 |
|
62 |
|
63 |
### Framework versions
|
|
|
17 |
|
18 |
This model is a fine-tuned version of [openai/whisper-base.en](https://huggingface.co/openai/whisper-base.en) on an unknown dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 1.1914
|
21 |
+
- Rouge1: 30.2379
|
22 |
+
- Rouge2: 8.3781
|
23 |
+
- Rougel: 25.6302
|
24 |
+
- Rougelsum: 25.6217
|
25 |
+
- Gen Len: 63.09
|
26 |
|
27 |
## Model description
|
28 |
|
|
|
51 |
|
52 |
### Training results
|
53 |
|
54 |
+
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|
55 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------:|:-------:|:---------:|:-------:|
|
56 |
+
| 3.0989 | 1.0 | 959 | 2.7267 | 22.3544 | 3.7732 | 21.0972 | 21.1155 | 58.46 |
|
57 |
+
| 2.2959 | 2.0 | 1918 | 2.1774 | 23.3309 | 3.946 | 21.5505 | 21.497 | 61.0 |
|
58 |
+
| 1.8902 | 3.0 | 2877 | 1.7126 | 26.1869 | 5.372 | 23.7001 | 23.6849 | 61.0 |
|
59 |
+
| 1.5533 | 4.0 | 3836 | 1.3554 | 29.4291 | 7.42 | 25.1978 | 25.1515 | 62.55 |
|
60 |
+
| 1.2635 | 5.0 | 4795 | 1.1914 | 30.2379 | 8.3781 | 25.6302 | 25.6217 | 63.09 |
|
61 |
|
62 |
|
63 |
### Framework versions
|