Commit
•
bbdef69
1
Parent(s):
4b76093
update model card README.md
Browse files
README.md
CHANGED
|
@@ -18,8 +18,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MULTILINGUAL_LIBRISPEECH - GERMAN dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
-
- Loss: 0.
|
| 22 |
-
- Wer: 0.
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
@@ -45,26 +45,40 @@ The following hyperparameters were used during training:
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
-
- num_epochs:
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
-
| Training Loss | Epoch
|
| 54 |
-
|
| 55 |
-
| 2.9888 | 7.25
|
| 56 |
-
| 2.9313 | 14.49
|
| 57 |
-
| 1.068 | 21.74
|
| 58 |
-
| 0.8151 | 28.99
|
| 59 |
-
| 0.764 | 36.23
|
| 60 |
-
| 0.7332 | 43.48
|
| 61 |
-
| 0.5952 | 50.72
|
| 62 |
-
| 0.6655 | 57.97
|
| 63 |
-
| 0.574 | 65.22
|
| 64 |
-
| 0.6211 | 72.46
|
| 65 |
-
| 0.5883 | 79.71
|
| 66 |
-
| 0.5666 | 86.96
|
| 67 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 18 |
|
| 19 |
This model is a fine-tuned version of [facebook/wav2vec2-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) on the MULTILINGUAL_LIBRISPEECH - GERMAN dataset.
|
| 20 |
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.2219
|
| 22 |
+
- Wer: 0.1288
|
| 23 |
|
| 24 |
## Model description
|
| 25 |
|
|
|
|
| 45 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 46 |
- lr_scheduler_type: linear
|
| 47 |
- lr_scheduler_warmup_steps: 1000
|
| 48 |
+
- num_epochs: 200.0
|
| 49 |
- mixed_precision_training: Native AMP
|
| 50 |
|
| 51 |
### Training results
|
| 52 |
|
| 53 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 54 |
+
|:-------------:|:------:|:-----:|:---------------:|:------:|
|
| 55 |
+
| 2.9888 | 7.25 | 500 | 2.9192 | 1.0 |
|
| 56 |
+
| 2.9313 | 14.49 | 1000 | 2.8698 | 1.0 |
|
| 57 |
+
| 1.068 | 21.74 | 1500 | 0.2647 | 0.2565 |
|
| 58 |
+
| 0.8151 | 28.99 | 2000 | 0.2067 | 0.1719 |
|
| 59 |
+
| 0.764 | 36.23 | 2500 | 0.1975 | 0.1568 |
|
| 60 |
+
| 0.7332 | 43.48 | 3000 | 0.1812 | 0.1463 |
|
| 61 |
+
| 0.5952 | 50.72 | 3500 | 0.1923 | 0.1428 |
|
| 62 |
+
| 0.6655 | 57.97 | 4000 | 0.1900 | 0.1404 |
|
| 63 |
+
| 0.574 | 65.22 | 4500 | 0.1822 | 0.1370 |
|
| 64 |
+
| 0.6211 | 72.46 | 5000 | 0.1937 | 0.1355 |
|
| 65 |
+
| 0.5883 | 79.71 | 5500 | 0.1872 | 0.1335 |
|
| 66 |
+
| 0.5666 | 86.96 | 6000 | 0.1874 | 0.1324 |
|
| 67 |
+
| 0.5526 | 94.2 | 6500 | 0.1998 | 0.1368 |
|
| 68 |
+
| 0.5671 | 101.45 | 7000 | 0.2054 | 0.1365 |
|
| 69 |
+
| 0.5514 | 108.7 | 7500 | 0.1987 | 0.1340 |
|
| 70 |
+
| 0.5382 | 115.94 | 8000 | 0.2104 | 0.1344 |
|
| 71 |
+
| 0.5819 | 123.19 | 8500 | 0.2125 | 0.1334 |
|
| 72 |
+
| 0.5277 | 130.43 | 9000 | 0.2063 | 0.1330 |
|
| 73 |
+
| 0.4626 | 137.68 | 9500 | 0.2105 | 0.1310 |
|
| 74 |
+
| 0.5842 | 144.93 | 10000 | 0.2087 | 0.1307 |
|
| 75 |
+
| 0.535 | 152.17 | 10500 | 0.2137 | 0.1309 |
|
| 76 |
+
| 0.5081 | 159.42 | 11000 | 0.2215 | 0.1302 |
|
| 77 |
+
| 0.6033 | 166.67 | 11500 | 0.2162 | 0.1302 |
|
| 78 |
+
| 0.5549 | 173.91 | 12000 | 0.2198 | 0.1286 |
|
| 79 |
+
| 0.5389 | 181.16 | 12500 | 0.2241 | 0.1293 |
|
| 80 |
+
| 0.4912 | 188.41 | 13000 | 0.2190 | 0.1290 |
|
| 81 |
+
| 0.4671 | 195.65 | 13500 | 0.2218 | 0.1290 |
|
| 82 |
|
| 83 |
|
| 84 |
### Framework versions
|