Update README.md
Browse files
README.md
CHANGED
@@ -1,48 +1,48 @@
|
|
1 |
-
---
|
2 |
-
language: "fr"
|
3 |
-
thumbnail:
|
4 |
-
tags:
|
5 |
-
- wav2vec2
|
6 |
-
license: "apache-2.0"
|
7 |
-
---
|
8 |
-
|
9 |
-
# LeBenchmark: wav2vec2 base model trained on 1K hours of French *female-only* speech
|
10 |
-
|
11 |
-
|
12 |
-
LeBenchmark provides an ensemble of pretrained wav2vec2 models on different French datasets containing spontaneous, read, and broadcasted speech.
|
13 |
-
|
14 |
-
For more information about our gender study for SSL moddels, please refer to our paper at: [A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems]()
|
15 |
-
|
16 |
-
|
17 |
-
## Model and data descriptions
|
18 |
-
|
19 |
-
We release four gender-specific models trained on 1K hours of speech.
|
20 |
-
|
21 |
-
- [wav2vec2-FR-1K-Male-large](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Male-large/)
|
22 |
-
- [wav2vec2-FR-1k-Male-base](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Male-base/)
|
23 |
-
- [wav2vec2-FR-1K-Female-large](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Female-large/)
|
24 |
-
- [wav2vec2-FR-1K-Female-base](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Female-base/)
|
25 |
-
|
26 |
-
## Intended uses & limitations
|
27 |
-
|
28 |
-
Pretrained wav2vec2 models are distributed under the Apache-2.0 license. Hence, they can be reused extensively without strict limitations. However, benchmarks and data may be linked to corpora that are not completely open-sourced.
|
29 |
-
|
30 |
-
## Referencing our gender-specific models
|
31 |
-
```
|
32 |
-
@article{boito2022study,
|
33 |
-
title={A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems},
|
34 |
-
author={Marcely Zanon Boito and Laurent Besacier and Natalia Tomashenko and Yannick Est{\`e}ve},
|
35 |
-
journal={arXiv preprint arXiv:2204.01397},
|
36 |
-
year={2022}
|
37 |
-
}
|
38 |
-
```
|
39 |
-
## Referencing LeBenchmark
|
40 |
-
|
41 |
-
```
|
42 |
-
@inproceedings{evain2021task,
|
43 |
-
title={Task agnostic and task specific self-supervised learning from speech with \textit{LeBenchmark}},
|
44 |
-
author={Evain, Sol{\`e}ne and Nguyen, Ha and Le, Hang and Boito, Marcely Zanon and Mdhaffar, Salima and Alisamir, Sina and Tong, Ziyi and Tomashenko, Natalia and Dinarelli, Marco and Parcollet, Titouan and others},
|
45 |
-
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
|
46 |
-
year={2021}
|
47 |
-
}
|
48 |
```
|
1 |
+
---
|
2 |
+
language: "fr"
|
3 |
+
thumbnail:
|
4 |
+
tags:
|
5 |
+
- wav2vec2
|
6 |
+
license: "apache-2.0"
|
7 |
+
---
|
8 |
+
|
9 |
+
# LeBenchmark: wav2vec2 base model trained on 1K hours of French *female-only* speech
|
10 |
+
|
11 |
+
|
12 |
+
LeBenchmark provides an ensemble of pretrained wav2vec2 models on different French datasets containing spontaneous, read, and broadcasted speech.
|
13 |
+
|
14 |
+
For more information about our gender study for SSL moddels, please refer to our paper at: [A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems](https://arxiv.org/abs/2204.01397)
|
15 |
+
|
16 |
+
|
17 |
+
## Model and data descriptions
|
18 |
+
|
19 |
+
We release four gender-specific models trained on 1K hours of speech.
|
20 |
+
|
21 |
+
- [wav2vec2-FR-1K-Male-large](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Male-large/)
|
22 |
+
- [wav2vec2-FR-1k-Male-base](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Male-base/)
|
23 |
+
- [wav2vec2-FR-1K-Female-large](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Female-large/)
|
24 |
+
- [wav2vec2-FR-1K-Female-base](https://huggingface.co/LeBenchmark/wav2vec-FR-1K-Female-base/)
|
25 |
+
|
26 |
+
## Intended uses & limitations
|
27 |
+
|
28 |
+
Pretrained wav2vec2 models are distributed under the Apache-2.0 license. Hence, they can be reused extensively without strict limitations. However, benchmarks and data may be linked to corpora that are not completely open-sourced.
|
29 |
+
|
30 |
+
## Referencing our gender-specific models
|
31 |
+
```
|
32 |
+
@article{boito2022study,
|
33 |
+
title={A Study of Gender Impact in Self-supervised Models for Speech-to-Text Systems},
|
34 |
+
author={Marcely Zanon Boito and Laurent Besacier and Natalia Tomashenko and Yannick Est{\`e}ve},
|
35 |
+
journal={arXiv preprint arXiv:2204.01397},
|
36 |
+
year={2022}
|
37 |
+
}
|
38 |
+
```
|
39 |
+
## Referencing LeBenchmark
|
40 |
+
|
41 |
+
```
|
42 |
+
@inproceedings{evain2021task,
|
43 |
+
title={Task agnostic and task specific self-supervised learning from speech with \textit{LeBenchmark}},
|
44 |
+
author={Evain, Sol{\`e}ne and Nguyen, Ha and Le, Hang and Boito, Marcely Zanon and Mdhaffar, Salima and Alisamir, Sina and Tong, Ziyi and Tomashenko, Natalia and Dinarelli, Marco and Parcollet, Titouan and others},
|
45 |
+
booktitle={Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)},
|
46 |
+
year={2021}
|
47 |
+
}
|
48 |
```
|