Instructions to use fav-kky/wav2vec2-base-cs-de-100k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use fav-kky/wav2vec2-base-cs-de-100k with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForPreTraining processor = AutoProcessor.from_pretrained("fav-kky/wav2vec2-base-cs-de-100k") model = AutoModelForPreTraining.from_pretrained("fav-kky/wav2vec2-base-cs-de-100k", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -17,7 +17,9 @@ It has been released along with a paper **A Comparative Analysis of Bilingual an
|
|
| 17 |
Automatic Speech Recognition in Multilingual Oral History Archives** accepted to INTERSPEECH2024 conference.
|
| 18 |
|
| 19 |
## Paper
|
| 20 |
-
|
|
|
|
|
|
|
| 21 |
|
| 22 |
### All pre-trained models released along with the paper
|
| 23 |
- [fav-kky/wav2vec2-base-cs-50k](https://huggingface.co/fav-kky/wav2vec2-base-cs-50k) (monolingual Czech)
|
|
@@ -30,19 +32,14 @@ The pre-print of our paper is available at http://arxiv.org/abs/2407.17160.
|
|
| 30 |
## Citation
|
| 31 |
If you find this model useful, please cite our paper:
|
| 32 |
```
|
| 33 |
-
@inproceedings{
|
| 34 |
-
title
|
| 35 |
-
author
|
| 36 |
-
|
| 37 |
-
|
| 38 |
-
|
| 39 |
-
|
| 40 |
-
|
| 41 |
-
},
|
| 42 |
-
booktitle={Proc. Interspeech 2024},
|
| 43 |
-
note={In Press},
|
| 44 |
-
year={2024},
|
| 45 |
-
url={https://arxiv.org/abs/2407.17160},
|
| 46 |
}
|
| 47 |
```
|
| 48 |
|
|
|
|
| 17 |
Automatic Speech Recognition in Multilingual Oral History Archives** accepted to INTERSPEECH2024 conference.
|
| 18 |
|
| 19 |
## Paper
|
| 20 |
+
https://www.isca-archive.org/interspeech_2024/lehecka24_interspeech.pdf
|
| 21 |
+
|
| 22 |
+
Pre-print: http://arxiv.org/abs/2407.17160.
|
| 23 |
|
| 24 |
### All pre-trained models released along with the paper
|
| 25 |
- [fav-kky/wav2vec2-base-cs-50k](https://huggingface.co/fav-kky/wav2vec2-base-cs-50k) (monolingual Czech)
|
|
|
|
| 32 |
## Citation
|
| 33 |
If you find this model useful, please cite our paper:
|
| 34 |
```
|
| 35 |
+
@inproceedings{lehecka24_interspeech,
|
| 36 |
+
title = {A Comparative Analysis of Bilingual and Trilingual Wav2Vec Models for Automatic Speech Recognition in Multilingual Oral History Archives},
|
| 37 |
+
author = {Jan Lehečka and Josef V. Psutka and Lubos Smidl and Pavel Ircing and Josef Psutka},
|
| 38 |
+
year = {2024},
|
| 39 |
+
booktitle = {Interspeech 2024},
|
| 40 |
+
pages = {1285--1289},
|
| 41 |
+
doi = {10.21437/Interspeech.2024-472},
|
| 42 |
+
issn = {2958-1796},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 43 |
}
|
| 44 |
```
|
| 45 |
|