patrickvonplaten
commited on
Commit
•
bb5da74
1
Parent(s):
ef5b721
update model card README.md
Browse files
README.md
CHANGED
@@ -2,7 +2,6 @@
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
5 |
-
- google_colab
|
6 |
datasets:
|
7 |
- common_voice
|
8 |
model-index:
|
@@ -17,8 +16,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
17 |
|
18 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
19 |
It achieves the following results on the evaluation set:
|
20 |
-
- Loss: 0.
|
21 |
-
- Wer: 0.
|
22 |
|
23 |
## Model description
|
24 |
|
@@ -53,19 +52,19 @@ The following hyperparameters were used during training:
|
|
53 |
|
54 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
56 |
-
| 3.
|
57 |
-
| 0.
|
58 |
-
| 0.
|
59 |
-
| 0.
|
60 |
-
| 0.
|
61 |
-
| 0.
|
62 |
-
| 0.
|
63 |
-
| 0.
|
64 |
|
65 |
|
66 |
### Framework versions
|
67 |
|
68 |
- Transformers 4.11.3
|
69 |
-
- Pytorch 1.10.0+
|
70 |
-
- Datasets 1.
|
71 |
- Tokenizers 0.10.3
|
|
|
2 |
license: apache-2.0
|
3 |
tags:
|
4 |
- generated_from_trainer
|
|
|
5 |
datasets:
|
6 |
- common_voice
|
7 |
model-index:
|
|
|
16 |
|
17 |
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the common_voice dataset.
|
18 |
It achieves the following results on the evaluation set:
|
19 |
+
- Loss: 0.3864
|
20 |
+
- Wer: 0.3570
|
21 |
|
22 |
## Model description
|
23 |
|
|
|
52 |
|
53 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
54 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
55 |
+
| 3.8302 | 3.67 | 400 | 0.6702 | 0.6903 |
|
56 |
+
| 0.4098 | 7.34 | 800 | 0.4574 | 0.4939 |
|
57 |
+
| 0.1908 | 11.01 | 1200 | 0.4350 | 0.4557 |
|
58 |
+
| 0.1279 | 14.68 | 1600 | 0.4204 | 0.4213 |
|
59 |
+
| 0.0966 | 18.35 | 2000 | 0.4238 | 0.3991 |
|
60 |
+
| 0.0782 | 22.02 | 2400 | 0.3822 | 0.3906 |
|
61 |
+
| 0.0613 | 25.69 | 2800 | 0.3982 | 0.3714 |
|
62 |
+
| 0.0477 | 29.36 | 3200 | 0.3864 | 0.3570 |
|
63 |
|
64 |
|
65 |
### Framework versions
|
66 |
|
67 |
- Transformers 4.11.3
|
68 |
+
- Pytorch 1.10.0+cu113
|
69 |
+
- Datasets 1.18.3
|
70 |
- Tokenizers 0.10.3
|