Update README.md
Browse files
README.md
CHANGED
@@ -7,22 +7,32 @@ metrics:
|
|
7 |
- wer
|
8 |
- cer
|
9 |
pipeline_tag: automatic-speech-recognition
|
|
|
|
|
10 |
---
|
11 |
|
|
|
|
|
|
|
|
|
12 |
Authors:
|
13 |
-
1.
|
14 |
-
2.
|
15 |
-
3.
|
16 |
-
4.
|
17 |
-
|
18 |
-
|
19 |
-
|
20 |
-
|
21 |
-
|
22 |
-
|
23 |
-
|
24 |
-
|
25 |
-
|
26 |
-
|
27 |
-
|
28 |
-
|
|
|
|
|
|
|
|
|
|
7 |
- wer
|
8 |
- cer
|
9 |
pipeline_tag: automatic-speech-recognition
|
10 |
+
base_model:
|
11 |
+
- jonatasgrosman/wav2vec2-large-xlsr-53-russian
|
12 |
---
|
13 |
|
14 |
+
# Fine-tuned xlsr-53-russian large model for speech recognition in Macedonian
|
15 |
+
|
16 |
+
Fine-tuned [wav2vec2-large-xlsr-53-russian](jonatasgrosman/wav2vec2-large-xlsr-53-russian)
|
17 |
+
|
18 |
Authors:
|
19 |
+
1. Dejan Porjazovski
|
20 |
+
2. Ilina Jakimovska
|
21 |
+
3. Ordan Chukaliev
|
22 |
+
4. Nikola Stikov
|
23 |
+
|
24 |
+
This collaboration is part of the activities of the Center for Advanced Interdisciplinary Research (CAIR) at UKIM.
|
25 |
+
|
26 |
+
## Data used for training
|
27 |
+
|
28 |
+
In training of the model, we used the following data sources:
|
29 |
+
1. Digital Archive for Ethnological and Anthropological Resources (DAEAR) at the Institutе of Ethnology and Anthropology, PMF, UKIM.
|
30 |
+
2. Audio version of the international journal "EthnoAnthropoZoom" at the Institutе of Ethnology and Anthropology, PMF, UKIM.
|
31 |
+
3. The podcast "Обични луѓе" by Ilina Jakimovska.
|
32 |
+
4. The scientific videos from the series "Наука за деца", foundation KANTAROT.
|
33 |
+
5. Macedonian version of the Mozilla Common Voice (version 18).
|
34 |
+
|
35 |
+
|
36 |
+
## Usage
|
37 |
+
|
38 |
+
When using this model, make sure that your speech input is sampled at 16kHz.
|