karolnowakowski
commited on
Commit
•
ba98442
1
Parent(s):
ebff493
Update README.md
Browse files
README.md
CHANGED
@@ -1,3 +1,22 @@
|
|
1 |
---
|
|
|
|
|
|
|
2 |
license: apache-2.0
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language:
|
3 |
+
- multilingual
|
4 |
+
- ain
|
5 |
license: apache-2.0
|
6 |
---
|
7 |
+
|
8 |
+
## Wav2Vec2-Large-XLSR-53 pretrained on Ainu language data
|
9 |
+
|
10 |
+
This is a [wav2vec-large-xlsr-53](https://huggingface.co/facebook/wav2vec2-large-xlsr-53) model after continued pretraining for 100k steps on 234 hours of speech data in Sakhalin Ainu and Hokkaido Ainu.
|
11 |
+
For details, please refer to the [paper]() (coming soon).
|
12 |
+
|
13 |
+
## Citation
|
14 |
+
When using the model please cite the following paper (in press):
|
15 |
+
```bibtex
|
16 |
+
@article{nowakowski2022,
|
17 |
+
title={Adapting Multilingual Speech Representation Model for a New, Underresourced Language through Multilingual Fine-tuning and Continued Pretraining},
|
18 |
+
author={Nowakowski, Karol and Ptaszynski, Michal and Murasaki, Kyoko and Nieuważny, Jagna},
|
19 |
+
year={2022},
|
20 |
+
booktitle={}
|
21 |
+
}
|
22 |
+
```
|