Commit
•
b67bb8e
1
Parent(s):
4159c76
Update README.md
Browse files
README.md
CHANGED
|
@@ -9,6 +9,9 @@ license: apache-2.0
|
|
| 9 |
This is a [wav2vec-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) model after continued pretraining on speech data in Hokkaido Ainu and Sakhalin Ainu (see [wav2vec2-large-xlsr-53-pretrain-ain](https://huggingface.co/karolnowakowski/wav2vec2-large-xlsr-53-pretrain-ain)) and fine-tuning for automatic speech recognition on 10h of labeled Sakhalin Ainu data.
|
| 10 |
For details, please refer to the [paper](https://arxiv.org/abs/2301.07295).
|
| 11 |
|
|
|
|
|
|
|
|
|
|
| 12 |
|
| 13 |
## Citation
|
| 14 |
When using the model please cite the following paper:
|
|
|
|
| 9 |
This is a [wav2vec-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) model after continued pretraining on speech data in Hokkaido Ainu and Sakhalin Ainu (see [wav2vec2-large-xlsr-53-pretrain-ain](https://huggingface.co/karolnowakowski/wav2vec2-large-xlsr-53-pretrain-ain)) and fine-tuning for automatic speech recognition on 10h of labeled Sakhalin Ainu data.
|
| 10 |
For details, please refer to the [paper](https://arxiv.org/abs/2301.07295).
|
| 11 |
|
| 12 |
+
On our evaluation set, the model yielded the following results:
|
| 13 |
+
* CER: 9.7
|
| 14 |
+
* WER: 29.8
|
| 15 |
|
| 16 |
## Citation
|
| 17 |
When using the model please cite the following paper:
|