Steven Liu
commited on
Commit
•
abea97a
1
Parent(s):
05fb527
update model card README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
-
- Loss: 0.
|
20 |
- Wer: 1.0
|
21 |
|
22 |
## Model description
|
@@ -50,16 +50,16 @@ The following hyperparameters were used during training:
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
53 |
-
| 2.
|
54 |
-
| 1.
|
55 |
-
|
|
56 |
-
| 0.
|
57 |
-
| 0.
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
-
- Transformers 4.
|
63 |
- Pytorch 1.12.1+cu113
|
64 |
- Datasets 2.6.1
|
65 |
- Tokenizers 0.13.2
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-base](https://huggingface.co/facebook/wav2vec2-base) on the None dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.8540
|
20 |
- Wer: 1.0
|
21 |
|
22 |
## Model description
|
|
|
50 |
|
51 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
52 |
|:-------------:|:-----:|:----:|:---------------:|:---:|
|
53 |
+
| 2.6816 | 1.0 | 54 | 2.2369 | 1.0 |
|
54 |
+
| 1.1823 | 2.0 | 108 | 1.0223 | 1.0 |
|
55 |
+
| 1.0363 | 3.0 | 162 | 0.9690 | 1.0 |
|
56 |
+
| 0.896 | 4.0 | 216 | 0.9106 | 1.0 |
|
57 |
+
| 0.8138 | 5.0 | 270 | 0.8540 | 1.0 |
|
58 |
|
59 |
|
60 |
### Framework versions
|
61 |
|
62 |
+
- Transformers 4.25.0.dev0
|
63 |
- Pytorch 1.12.1+cu113
|
64 |
- Datasets 2.6.1
|
65 |
- Tokenizers 0.13.2
|