carlosdanielhernandezmena
commited on
Commit
•
189064e
1
Parent(s):
86a9a20
Poniendo la primera información en el README
Browse filesEsta es la primera información del README. Espero no tener que poner mucho más. Creo que solo falta el código de ejemplo para usar el modelo (usage).
README.md
CHANGED
@@ -1,3 +1,69 @@
|
|
1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
2 |
license: cc-by-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
3 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
---
|
2 |
+
language: fo
|
3 |
+
datasets:
|
4 |
+
- ravnursson
|
5 |
+
tags:
|
6 |
+
- audio
|
7 |
+
- automatic-speech-recognition
|
8 |
+
- faroese
|
9 |
+
- xlrs-53-faroese
|
10 |
+
- ravnur-project
|
11 |
+
- faroe-islands
|
12 |
license: cc-by-4.0
|
13 |
+
widget:
|
14 |
+
model-index:
|
15 |
+
- name: wav2vec2-large-xlsr-53-faroese-100h
|
16 |
+
results:
|
17 |
+
- task:
|
18 |
+
name: Automatic Speech Recognition
|
19 |
+
type: automatic-speech-recognition
|
20 |
+
dataset:
|
21 |
+
name: Ravnursson Faroese Speech and Transcripts
|
22 |
+
type: read
|
23 |
+
split: test
|
24 |
+
args:
|
25 |
+
language: fo
|
26 |
+
metrics:
|
27 |
+
- name: Test WER
|
28 |
+
type: wer
|
29 |
+
value: 0.076
|
30 |
+
- task:
|
31 |
+
name: Automatic Speech Recognition
|
32 |
+
type: automatic-speech-recognition
|
33 |
+
dataset:
|
34 |
+
name: Ravnursson Faroese Speech and Transcripts
|
35 |
+
type: read
|
36 |
+
split: dev
|
37 |
+
args:
|
38 |
+
language: fo
|
39 |
+
metrics:
|
40 |
+
- name: Test WER
|
41 |
+
type: wer
|
42 |
+
value: 0.00556
|
43 |
---
|
44 |
+
|
45 |
+
# wav2vec2-large-xlsr-53-faroese-100h
|
46 |
+
|
47 |
+
The "wav2vec2-large-xlsr-53-faroese-100h" is an acoustic model suitable for Automatic Speech Recognition in Faroese. It is the result of fine-tuning the model "facebook/wav2vec2-large-xlsr-53" with 100 hours of Faroese data released by the Ravnur Project (https://maltokni.fo/en/) from the Faroe Islands.
|
48 |
+
|
49 |
+
The specific dataset used to create the model is called "Ravnursson Faroese Speech and Transcripts" and it is available at http://hdl.handle.net/20.500.12537/276.
|
50 |
+
|
51 |
+
The fine-tuning process was perform during November (2022) in the servers of the Language and Voice Lab (https://lvl.ru.is/) at Reykjavík University (Iceland) by Carlos Daniel Hernández Mena.
|
52 |
+
|
53 |
+
# BibTeX entry and citation info
|
54 |
+
*When publishing results based on these models please refer to:*
|
55 |
+
```bibtex
|
56 |
+
@misc{mena2022xlrs53faroese,
|
57 |
+
title={Acoustic Model in Faroese: wav2vec2-large-xlsr-53-faroese-100h.},
|
58 |
+
author={Hernandez Mena, Carlos Daniel},
|
59 |
+
year={2022},
|
60 |
+
url={https://huggingface.co/carlosdanielhernandezmena/wav2vec2-large-xlsr-53-faroese-100h},
|
61 |
+
}
|
62 |
+
```
|
63 |
+
|
64 |
+
# Acknowledgements
|
65 |
+
|
66 |
+
We want to thank to Jón Guðnason, head of the Language and Voice Lab for providing computational power to make this model possible. We also want to thank to the "Language Technology Programme for Icelandic 2019-2023" which is managed and coordinated by Almannarómur, and it is funded by the Icelandic Ministry of Education, Science and Culture.
|
67 |
+
|
68 |
+
Special thanks to Annika Simonsen and to The Ravnur Project for making their
|
69 |
+
"Basic Language Resource Kit"(BLARK 1.0) publicly available through the research paper "Creating a Basic Language Resource Kit for Faroese" https://aclanthology.org/2022.lrec-1.495.pdf
|