update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,9 +16,9 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 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 None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss: 0.
|
| 20 |
-
- Wer: 0.
|
| 21 |
-
- Cer: 0.
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
@@ -53,41 +53,41 @@ The following hyperparameters were used during training:
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 56 |
-
| 17.
|
| 57 |
-
| 3.
|
| 58 |
-
| 3.
|
| 59 |
-
| 3.
|
| 60 |
-
| 3.
|
| 61 |
-
|
|
| 62 |
-
| 2.
|
| 63 |
-
|
|
| 64 |
-
|
|
| 65 |
-
| 0.
|
| 66 |
-
| 0.
|
| 67 |
-
| 0.
|
| 68 |
-
| 0.
|
| 69 |
-
| 0.
|
| 70 |
-
| 0.
|
| 71 |
-
| 0.
|
| 72 |
-
| 0.
|
| 73 |
-
| 0.
|
| 74 |
-
| 0.
|
| 75 |
-
| 0.
|
| 76 |
-
| 0.
|
| 77 |
-
| 0.
|
| 78 |
-
| 0.
|
| 79 |
-
| 0.
|
| 80 |
-
| 0.
|
| 81 |
-
| 0.
|
| 82 |
-
| 0.
|
| 83 |
-
| 0.
|
| 84 |
-
| 0.
|
| 85 |
-
| 0.
|
| 86 |
|
| 87 |
|
| 88 |
### Framework versions
|
| 89 |
|
| 90 |
- Transformers 4.26.1
|
| 91 |
- Pytorch 1.13.1+cu116
|
| 92 |
-
- Datasets 2.
|
| 93 |
- Tokenizers 0.13.2
|
|
|
|
| 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 None dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
+
- Loss: 0.0021
|
| 20 |
+
- Wer: 0.0191
|
| 21 |
+
- Cer: 0.0072
|
| 22 |
|
| 23 |
## Model description
|
| 24 |
|
|
|
|
| 53 |
|
| 54 |
| Training Loss | Epoch | Step | Validation Loss | Wer | Cer |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|
|
| 56 |
+
| 17.5531 | 1.0 | 51 | 5.2205 | 1.0 | 1.0 |
|
| 57 |
+
| 3.9441 | 2.0 | 102 | 3.1378 | 1.0 | 1.0 |
|
| 58 |
+
| 3.1686 | 3.0 | 153 | 3.1191 | 1.0 | 1.0 |
|
| 59 |
+
| 3.1558 | 4.0 | 204 | 3.1101 | 1.0 | 1.0 |
|
| 60 |
+
| 3.1286 | 5.0 | 255 | 3.0171 | 1.0 | 1.0 |
|
| 61 |
+
| 3.0755 | 6.0 | 306 | 2.9542 | 1.0 | 1.0 |
|
| 62 |
+
| 2.9533 | 7.0 | 357 | 2.8221 | 1.0 | 1.0 |
|
| 63 |
+
| 2.5924 | 8.0 | 408 | 2.1453 | 1.0 | 0.9771 |
|
| 64 |
+
| 1.8657 | 9.0 | 459 | 1.1540 | 0.9094 | 0.7057 |
|
| 65 |
+
| 0.9519 | 10.0 | 510 | 0.4219 | 0.6767 | 0.2782 |
|
| 66 |
+
| 0.4752 | 11.0 | 561 | 0.1646 | 0.3416 | 0.0870 |
|
| 67 |
+
| 0.2402 | 12.0 | 612 | 0.0551 | 0.0899 | 0.0255 |
|
| 68 |
+
| 0.1512 | 13.0 | 663 | 0.0307 | 0.0586 | 0.0167 |
|
| 69 |
+
| 0.0906 | 14.0 | 714 | 0.0172 | 0.0541 | 0.0161 |
|
| 70 |
+
| 0.0711 | 15.0 | 765 | 0.0141 | 0.0444 | 0.0125 |
|
| 71 |
+
| 0.0561 | 16.0 | 816 | 0.0114 | 0.0269 | 0.0065 |
|
| 72 |
+
| 0.048 | 17.0 | 867 | 0.0090 | 0.0338 | 0.0110 |
|
| 73 |
+
| 0.0452 | 18.0 | 918 | 0.0072 | 0.0235 | 0.0080 |
|
| 74 |
+
| 0.0349 | 19.0 | 969 | 0.0073 | 0.0207 | 0.0062 |
|
| 75 |
+
| 0.0333 | 20.0 | 1020 | 0.0054 | 0.0183 | 0.0055 |
|
| 76 |
+
| 0.0275 | 21.0 | 1071 | 0.0050 | 0.0280 | 0.0087 |
|
| 77 |
+
| 0.0262 | 22.0 | 1122 | 0.0039 | 0.0251 | 0.0088 |
|
| 78 |
+
| 0.0241 | 23.0 | 1173 | 0.0039 | 0.0302 | 0.0110 |
|
| 79 |
+
| 0.0216 | 24.0 | 1224 | 0.0035 | 0.0243 | 0.0086 |
|
| 80 |
+
| 0.019 | 25.0 | 1275 | 0.0033 | 0.0250 | 0.0091 |
|
| 81 |
+
| 0.0178 | 26.0 | 1326 | 0.0027 | 0.0238 | 0.0089 |
|
| 82 |
+
| 0.0169 | 27.0 | 1377 | 0.0025 | 0.0220 | 0.0080 |
|
| 83 |
+
| 0.0168 | 28.0 | 1428 | 0.0024 | 0.0175 | 0.0060 |
|
| 84 |
+
| 0.015 | 29.0 | 1479 | 0.0021 | 0.0194 | 0.0071 |
|
| 85 |
+
| 0.0131 | 30.0 | 1530 | 0.0021 | 0.0191 | 0.0072 |
|
| 86 |
|
| 87 |
|
| 88 |
### Framework versions
|
| 89 |
|
| 90 |
- Transformers 4.26.1
|
| 91 |
- Pytorch 1.13.1+cu116
|
| 92 |
+
- Datasets 2.10.0
|
| 93 |
- Tokenizers 0.13.2
|