Model save
Browse files- README.md +12 -12
- model.safetensors +1 -1
README.md
CHANGED
@@ -19,8 +19,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
19 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.3748
|
22 |
-
- Wer:
|
23 |
-
- Cer:
|
24 |
|
25 |
## Model description
|
26 |
|
@@ -53,16 +53,16 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
55 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:-------:|
|
56 |
-
| 3.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
-
| 0.
|
65 |
-
| 0.
|
66 |
|
67 |
|
68 |
### Framework versions
|
|
|
19 |
This model is a fine-tuned version of [openai/whisper-base](https://huggingface.co/openai/whisper-base) on an unknown dataset.
|
20 |
It achieves the following results on the evaluation set:
|
21 |
- Loss: 0.3748
|
22 |
+
- Wer: 90.8832
|
23 |
+
- Cer: 69.2460
|
24 |
|
25 |
## Model description
|
26 |
|
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
55 |
|:-------------:|:-------:|:----:|:---------------:|:--------:|:-------:|
|
56 |
+
| 3.8293 | 4.5872 | 500 | 3.9014 | 98.4330 | 73.8234 |
|
57 |
+
| 0.9253 | 9.1743 | 1000 | 1.1787 | 101.2821 | 77.9887 |
|
58 |
+
| 0.3997 | 13.7615 | 1500 | 0.6684 | 98.9079 | 76.8980 |
|
59 |
+
| 0.3313 | 18.3486 | 2000 | 0.4931 | 97.4359 | 79.5259 |
|
60 |
+
| 0.2974 | 22.9358 | 2500 | 0.4656 | 109.0693 | 83.0385 |
|
61 |
+
| 0.2635 | 27.5229 | 3000 | 0.4219 | 103.5138 | 78.6843 |
|
62 |
+
| 0.2241 | 32.1101 | 3500 | 0.4047 | 100.5698 | 77.2587 |
|
63 |
+
| 0.1939 | 36.6972 | 4000 | 0.3893 | 89.9810 | 69.3404 |
|
64 |
+
| 0.1718 | 41.2844 | 4500 | 0.3807 | 87.8443 | 67.3738 |
|
65 |
+
| 0.1471 | 45.8716 | 5000 | 0.3748 | 90.8832 | 69.2460 |
|
66 |
|
67 |
|
68 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290403936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cce1cf73eccfb7ada9d561d23b93e929099f135d5902518c4338b023e15f6c1e
|
3 |
size 290403936
|