Commit
•
3a6bfec
1
Parent(s):
260a26e
update model card README.md
Browse files
README.md
CHANGED
@@ -16,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
-
- Wer:
|
21 |
|
22 |
## Model description
|
23 |
|
@@ -50,21 +50,21 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
53 |
-
| 1.
|
54 |
-
| 1.
|
55 |
-
| 0.
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
-
- Transformers 4.
|
68 |
- Pytorch 2.0.0+cu118
|
69 |
- Datasets 2.11.0
|
70 |
- Tokenizers 0.13.3
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3901
|
20 |
+
- Wer: 20.1074
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
53 |
+
| 1.8697 | 2.08 | 100 | 1.5724 | 43.7232 |
|
54 |
+
| 1.2267 | 4.17 | 200 | 0.8637 | 90.9905 |
|
55 |
+
| 0.6451 | 6.25 | 300 | 0.6205 | 85.8473 |
|
56 |
+
| 0.4958 | 8.33 | 400 | 0.5447 | 93.4368 |
|
57 |
+
| 0.4053 | 10.42 | 500 | 0.4883 | 52.0644 |
|
58 |
+
| 0.3149 | 12.5 | 600 | 0.4480 | 32.4821 |
|
59 |
+
| 0.2608 | 14.58 | 700 | 0.4218 | 24.0334 |
|
60 |
+
| 0.2245 | 16.67 | 800 | 0.4045 | 22.0764 |
|
61 |
+
| 0.2038 | 18.75 | 900 | 0.3937 | 19.5227 |
|
62 |
+
| 0.183 | 20.83 | 1000 | 0.3901 | 20.1074 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
+
- Transformers 4.28.0
|
68 |
- Pytorch 2.0.0+cu118
|
69 |
- Datasets 2.11.0
|
70 |
- Tokenizers 0.13.3
|