Update README.md
Browse files
README.md
CHANGED
@@ -16,7 +16,7 @@ The large model pre-trained on 16kHz sampled speech audio with [facebook/wav2vec
|
|
16 |
|
17 |
The Finnish Wav2Vec2 Base has the same architecture and uses the same training objective as the English and multilingual one described in [Paper](https://arxiv.org/abs/2006.11477). It is pre-trained on 2600 hours of unlabeled colloquial Finnish speech from [Lahjoita puhetta (Donate Speech)](https://link.springer.com/article/10.1007/s10579-022-09606-3).
|
18 |
|
19 |
-
You can read more about the pre-trained model from [this paper](
|
20 |
|
21 |
## Intended uses & limitations
|
22 |
|
@@ -37,15 +37,14 @@ The model was pre-trained on the data from the [Lahjoita puhetta (Donate Speech)
|
|
37 |
If you use our models or scripts, please cite our article as:
|
38 |
|
39 |
```bibtex
|
40 |
-
@inproceedings{
|
41 |
-
|
42 |
-
|
43 |
-
|
44 |
-
year=2024,
|
45 |
-
booktitle={
|
46 |
-
pages={
|
47 |
-
doi={
|
48 |
-
issn={XXXX-XXXX}
|
49 |
}
|
50 |
```
|
51 |
|
|
|
16 |
|
17 |
The Finnish Wav2Vec2 Base has the same architecture and uses the same training objective as the English and multilingual one described in [Paper](https://arxiv.org/abs/2006.11477). It is pre-trained on 2600 hours of unlabeled colloquial Finnish speech from [Lahjoita puhetta (Donate Speech)](https://link.springer.com/article/10.1007/s10579-022-09606-3).
|
18 |
|
19 |
+
You can read more about the pre-trained model from [this paper](https://www.isca-archive.org/interspeech_2024/getman24_interspeech.html). The training scripts are available on [GitHub](https://github.com/aalto-speech/colloquial-Finnish-wav2vec2)
|
20 |
|
21 |
## Intended uses & limitations
|
22 |
|
|
|
37 |
If you use our models or scripts, please cite our article as:
|
38 |
|
39 |
```bibtex
|
40 |
+
@inproceedings{getman24_interspeech,
|
41 |
+
title = {What happens in continued pre-training? Analysis of self-supervised speech
|
42 |
+
models with continued pre-training for colloquial Finnish ASR},
|
43 |
+
author = {Yaroslav Getman and Tamas Grosz and Mikko Kurimo},
|
44 |
+
year = {2024},
|
45 |
+
booktitle = {Interspeech 2024},
|
46 |
+
pages = {5043--5047},
|
47 |
+
doi = {10.21437/Interspeech.2024-476},
|
|
|
48 |
}
|
49 |
```
|
50 |
|