Update README.md
Browse files
README.md
CHANGED
|
@@ -27,15 +27,14 @@ model-index:
|
|
| 27 |
type: cer
|
| 28 |
value: 13.3
|
| 29 |
---
|
| 30 |
-
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 31 |
-
should probably proofread and complete it, then remove this comment. -->
|
| 32 |
|
| 33 |
# wav2vec2-xls-r-300m-cs-cv8
|
| 34 |
|
| 35 |
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 8.0 dataset.
|
| 36 |
It achieves the following results on the evaluation set:
|
| 37 |
-
|
| 38 |
-
|
|
|
|
| 39 |
|
| 40 |
## Usage
|
| 41 |
|
|
@@ -84,8 +83,6 @@ python eval.py --model_id comodoro/wav2vec2-xls-r-300m-sk-cv8 --dataset mozilla-
|
|
| 84 |
|
| 85 |
The Common Voice 8.0 `train` and `validation` datasets were used for training
|
| 86 |
|
| 87 |
-
## Training procedure
|
| 88 |
-
|
| 89 |
### Training hyperparameters
|
| 90 |
|
| 91 |
The following hyperparameters were used during training:
|
|
|
|
| 27 |
type: cer
|
| 28 |
value: 13.3
|
| 29 |
---
|
|
|
|
|
|
|
| 30 |
|
| 31 |
# wav2vec2-xls-r-300m-cs-cv8
|
| 32 |
|
| 33 |
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 8.0 dataset.
|
| 34 |
It achieves the following results on the evaluation set:
|
| 35 |
+
|
| 36 |
+
- WER: 0.49575384615384616
|
| 37 |
+
- CER: 0.13333333333333333
|
| 38 |
|
| 39 |
## Usage
|
| 40 |
|
|
|
|
| 83 |
|
| 84 |
The Common Voice 8.0 `train` and `validation` datasets were used for training
|
| 85 |
|
|
|
|
|
|
|
| 86 |
### Training hyperparameters
|
| 87 |
|
| 88 |
The following hyperparameters were used during training:
|