update model card README.md
Browse files
README.md
CHANGED
|
@@ -33,8 +33,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 33 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.5728
|
| 36 |
-
- Wer Ortho: 0.3943
|
| 37 |
- Wer: 0.3664
|
|
|
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
@@ -64,28 +64,28 @@ The following hyperparameters were used during training:
|
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer Ortho |
|
| 68 |
-
|
| 69 |
-
| 0.7731 | 1.45 | 100 | 0.7280 | 0.
|
| 70 |
-
| 0.2103 | 2.9 | 200 | 0.5116 | 0.
|
| 71 |
-
| 0.0633 | 4.35 | 300 | 0.4967 | 0.
|
| 72 |
-
| 0.0249 | 5.8 | 400 | 0.5003 | 0.
|
| 73 |
-
| 0.0143 | 7.25 | 500 | 0.5191 | 0.
|
| 74 |
-
| 0.0053 | 8.7 | 600 | 0.5149 | 0.
|
| 75 |
-
| 0.0035 | 10.14 | 700 | 0.5345 | 0.
|
| 76 |
-
| 0.0027 | 11.59 | 800 | 0.5339 | 0.
|
| 77 |
-
| 0.0026 | 13.04 | 900 | 0.5435 | 0.
|
| 78 |
-
| 0.0037 | 14.49 | 1000 | 0.5346 | 0.
|
| 79 |
-
| 0.0045 | 15.94 | 1100 | 0.5438 | 0.
|
| 80 |
-
| 0.0028 | 17.39 | 1200 | 0.5588 | 0.
|
| 81 |
-
| 0.0036 | 18.84 | 1300 | 0.5466 | 0.
|
| 82 |
-
| 0.0035 | 20.29 | 1400 | 0.5364 | 0.
|
| 83 |
-
| 0.0056 | 21.74 | 1500 | 0.5608 | 0.
|
| 84 |
-
| 0.0037 | 23.19 | 1600 | 0.5443 | 0.
|
| 85 |
-
| 0.0035 | 24.64 | 1700 | 0.5466 | 0.
|
| 86 |
-
| 0.0024 | 26.09 | 1800 | 0.5628 | 0.
|
| 87 |
-
| 0.0036 | 27.54 | 1900 | 0.5495 | 0.
|
| 88 |
-
| 0.0016 | 28.99 | 2000 | 0.5728 | 0.
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|
|
|
|
| 33 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the google/fleurs dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
- Loss: 0.5728
|
|
|
|
| 36 |
- Wer: 0.3664
|
| 37 |
+
- Wer Ortho: 0.3943
|
| 38 |
|
| 39 |
## Model description
|
| 40 |
|
|
|
|
| 64 |
|
| 65 |
### Training results
|
| 66 |
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer | Wer Ortho |
|
| 68 |
+
|:-------------:|:-----:|:----:|:---------------:|:------:|:---------:|
|
| 69 |
+
| 0.7731 | 1.45 | 100 | 0.7280 | 0.3740 | 0.3863 |
|
| 70 |
+
| 0.2103 | 2.9 | 200 | 0.5116 | 0.3661 | 0.3859 |
|
| 71 |
+
| 0.0633 | 4.35 | 300 | 0.4967 | 0.2810 | 0.3008 |
|
| 72 |
+
| 0.0249 | 5.8 | 400 | 0.5003 | 0.3299 | 0.3477 |
|
| 73 |
+
| 0.0143 | 7.25 | 500 | 0.5191 | 0.3510 | 0.3660 |
|
| 74 |
+
| 0.0053 | 8.7 | 600 | 0.5149 | 0.3070 | 0.3221 |
|
| 75 |
+
| 0.0035 | 10.14 | 700 | 0.5345 | 0.3266 | 0.3443 |
|
| 76 |
+
| 0.0027 | 11.59 | 800 | 0.5339 | 0.3175 | 0.3344 |
|
| 77 |
+
| 0.0026 | 13.04 | 900 | 0.5435 | 0.3134 | 0.3328 |
|
| 78 |
+
| 0.0037 | 14.49 | 1000 | 0.5346 | 0.2506 | 0.2714 |
|
| 79 |
+
| 0.0045 | 15.94 | 1100 | 0.5438 | 0.3220 | 0.3389 |
|
| 80 |
+
| 0.0028 | 17.39 | 1200 | 0.5588 | 0.2551 | 0.2740 |
|
| 81 |
+
| 0.0036 | 18.84 | 1300 | 0.5466 | 0.2728 | 0.2702 |
|
| 82 |
+
| 0.0035 | 20.29 | 1400 | 0.5364 | 0.3119 | 0.3332 |
|
| 83 |
+
| 0.0056 | 21.74 | 1500 | 0.5608 | 0.2506 | 0.2721 |
|
| 84 |
+
| 0.0037 | 23.19 | 1600 | 0.5443 | 0.2833 | 0.3027 |
|
| 85 |
+
| 0.0035 | 24.64 | 1700 | 0.5466 | 0.3631 | 0.3866 |
|
| 86 |
+
| 0.0024 | 26.09 | 1800 | 0.5628 | 0.3198 | 0.3416 |
|
| 87 |
+
| 0.0036 | 27.54 | 1900 | 0.5495 | 0.2946 | 0.3122 |
|
| 88 |
+
| 0.0016 | 28.99 | 2000 | 0.5728 | 0.3664 | 0.3943 |
|
| 89 |
|
| 90 |
|
| 91 |
### Framework versions
|