Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,8 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# wav2vec2-large-xls-r-300m-dansk-CV-80
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m)
|
|
|
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- eval_loss: 0.6394
|
| 20 |
- eval_wer: 0.3682
|
|
@@ -26,7 +27,7 @@ It achieves the following results on the evaluation set:
|
|
| 26 |
|
| 27 |
## Model description
|
| 28 |
|
| 29 |
-
|
| 30 |
|
| 31 |
## Intended uses & limitations
|
| 32 |
|
|
@@ -34,7 +35,7 @@ More information needed
|
|
| 34 |
|
| 35 |
## Training and evaluation data
|
| 36 |
|
| 37 |
-
|
| 38 |
|
| 39 |
## Training procedure
|
| 40 |
|
|
|
|
| 14 |
|
| 15 |
# wav2vec2-large-xls-r-300m-dansk-CV-80
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [facebook/wav2vec2-xls-r-300m](https://huggingface.co/facebook/wav2vec2-xls-r-300m) for Danish, using the [mozilla-foundation/common_voice_8_0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0) dataset.
|
| 18 |
+
|
| 19 |
It achieves the following results on the evaluation set:
|
| 20 |
- eval_loss: 0.6394
|
| 21 |
- eval_wer: 0.3682
|
|
|
|
| 27 |
|
| 28 |
## Model description
|
| 29 |
|
| 30 |
+
ASR Danish model
|
| 31 |
|
| 32 |
## Intended uses & limitations
|
| 33 |
|
|
|
|
| 35 |
|
| 36 |
## Training and evaluation data
|
| 37 |
|
| 38 |
+
Danish subset of [mozilla-foundation/common_voice_8_0](https://huggingface.co/datasets/mozilla-foundation/common_voice_8_0)
|
| 39 |
|
| 40 |
## Training procedure
|
| 41 |
|