Update README.md
Browse files
README.md
CHANGED
|
@@ -29,9 +29,6 @@ model-index:
|
|
| 29 |
value: 14.3
|
| 30 |
---
|
| 31 |
|
| 32 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 33 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 34 |
-
|
| 35 |
# Upper Sorbian wav2vec2-xls-r-300m-hsb-cv8
|
| 36 |
|
| 37 |
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.
|
|
@@ -40,19 +37,12 @@ It achieves the following results on the evaluation set:
|
|
| 40 |
- Wer: 0.5037
|
| 41 |
- Cer: 0.1278
|
| 42 |
|
| 43 |
-
##
|
| 44 |
-
|
| 45 |
-
More information needed
|
| 46 |
-
|
| 47 |
-
## Intended uses & limitations
|
| 48 |
-
|
| 49 |
-
More information needed
|
| 50 |
-
|
| 51 |
-
## Training and evaluation data
|
| 52 |
-
|
| 53 |
-
More information needed
|
| 54 |
|
| 55 |
-
|
|
|
|
|
|
|
|
|
|
| 56 |
|
| 57 |
### Training hyperparameters
|
| 58 |
|
|
|
|
| 29 |
value: 14.3
|
| 30 |
---
|
| 31 |
|
|
|
|
|
|
|
|
|
|
| 32 |
# Upper Sorbian wav2vec2-xls-r-300m-hsb-cv8
|
| 33 |
|
| 34 |
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.
|
|
|
|
| 37 |
- Wer: 0.5037
|
| 38 |
- Cer: 0.1278
|
| 39 |
|
| 40 |
+
## Evaluation
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
+
The model can be evaluated using the attached `eval.py` script:
|
| 43 |
+
```
|
| 44 |
+
python eval.py --model_id comodoro/wav2vec2-xls-r-300m-hsb-cv8 --dataset mozilla-foundation/common-voice_8_0 --split test --config hsb
|
| 45 |
+
```
|
| 46 |
|
| 47 |
### Training hyperparameters
|
| 48 |
|