update model card README.md
Browse files
README.md
CHANGED
|
@@ -16,8 +16,8 @@ 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 common_voice dataset.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
-
- Loss:
|
| 20 |
-
- Wer: 0.
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -37,7 +37,7 @@ More information needed
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0003
|
| 40 |
-
- train_batch_size:
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- distributed_type: multi-GPU
|
|
@@ -51,7 +51,22 @@ The following hyperparameters were used during training:
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 55 |
|
| 56 |
|
| 57 |
### Framework versions
|
|
|
|
| 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: 0.4121
|
| 20 |
+
- Wer: 0.3112
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
|
|
| 37 |
|
| 38 |
The following hyperparameters were used during training:
|
| 39 |
- learning_rate: 0.0003
|
| 40 |
+
- train_batch_size: 16
|
| 41 |
- eval_batch_size: 8
|
| 42 |
- seed: 42
|
| 43 |
- distributed_type: multi-GPU
|
|
|
|
| 51 |
|
| 52 |
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 53 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 54 |
+
| 4.1868 | 1.83 | 400 | 0.9812 | 0.8398 |
|
| 55 |
+
| 0.691 | 3.67 | 800 | 0.5571 | 0.6298 |
|
| 56 |
+
| 0.3555 | 5.5 | 1200 | 0.4676 | 0.4779 |
|
| 57 |
+
| 0.2451 | 7.34 | 1600 | 0.4572 | 0.4541 |
|
| 58 |
+
| 0.1844 | 9.17 | 2000 | 0.4743 | 0.4389 |
|
| 59 |
+
| 0.1541 | 11.01 | 2400 | 0.4583 | 0.4300 |
|
| 60 |
+
| 0.1277 | 12.84 | 2800 | 0.4565 | 0.3950 |
|
| 61 |
+
| 0.1122 | 14.68 | 3200 | 0.4761 | 0.4087 |
|
| 62 |
+
| 0.0975 | 16.51 | 3600 | 0.4654 | 0.3786 |
|
| 63 |
+
| 0.0861 | 18.35 | 4000 | 0.4503 | 0.3667 |
|
| 64 |
+
| 0.0775 | 20.18 | 4400 | 0.4600 | 0.3581 |
|
| 65 |
+
| 0.0666 | 22.02 | 4800 | 0.4350 | 0.3504 |
|
| 66 |
+
| 0.0627 | 23.85 | 5200 | 0.4211 | 0.3349 |
|
| 67 |
+
| 0.0558 | 25.69 | 5600 | 0.4390 | 0.3333 |
|
| 68 |
+
| 0.0459 | 27.52 | 6000 | 0.4218 | 0.3185 |
|
| 69 |
+
| 0.0439 | 29.36 | 6400 | 0.4121 | 0.3112 |
|
| 70 |
|
| 71 |
|
| 72 |
### Framework versions
|