Commit
•
b029bba
1
Parent(s):
ba31ea0
Update README.md
Browse files
README.md
CHANGED
|
@@ -29,24 +29,10 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 29 |
|
| 30 |
# xls-r-fleurs_nl-run1
|
| 31 |
|
| 32 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
-
-
|
| 35 |
-
- Wer:
|
| 36 |
-
|
| 37 |
-
## Model description
|
| 38 |
-
|
| 39 |
-
More information needed
|
| 40 |
-
|
| 41 |
-
## Intended uses & limitations
|
| 42 |
-
|
| 43 |
-
More information needed
|
| 44 |
-
|
| 45 |
-
## Training and evaluation data
|
| 46 |
-
|
| 47 |
-
More information needed
|
| 48 |
-
|
| 49 |
-
## Training procedure
|
| 50 |
|
| 51 |
### Training hyperparameters
|
| 52 |
|
|
@@ -65,7 +51,7 @@ The following hyperparameters were used during training:
|
|
| 65 |
|
| 66 |
### Training results
|
| 67 |
|
| 68 |
-
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 69 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 70 |
| 4.9153 | 1.03 | 250 | 2.9252 | 1.0 |
|
| 71 |
| 2.6885 | 2.05 | 500 | 1.2362 | 0.8548 |
|
|
|
|
| 29 |
|
| 30 |
# xls-r-fleurs_nl-run1
|
| 31 |
|
| 32 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) on the FLEURS (nl) dataset.
|
| 33 |
It achieves the following results on the evaluation set:
|
| 34 |
+
- Wer (Validation): 40.36%
|
| 35 |
+
- Wer (Test): 40.73%
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
|
| 37 |
### Training hyperparameters
|
| 38 |
|
|
|
|
| 51 |
|
| 52 |
### Training results
|
| 53 |
|
| 54 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer (Train) |
|
| 55 |
|:-------------:|:-----:|:----:|:---------------:|:------:|
|
| 56 |
| 4.9153 | 1.03 | 250 | 2.9252 | 1.0 |
|
| 57 |
| 2.6885 | 2.05 | 500 | 1.2362 | 0.8548 |
|