Update README.md
Browse files
README.md
CHANGED
|
@@ -1,10 +1,25 @@
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
---
|
| 4 |
|
| 5 |
-
|
| 6 |
|
| 7 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
|
| 9 |
| Model | CER | WER |
|
| 10 |
|-|-|-|
|
|
@@ -28,7 +43,8 @@ Metrics for the NEWS models (tested with an acoustic model of [wav2vec2-xls-r-30
|
|
| 28 |
| lm-4gram-500k | 0.0247 | 0.1207 |
|
| 29 |
| lm-5gram-500k | 0.0247 | 0.1209 |
|
| 30 |
|
| 31 |
-
Files of the models are under the Files and versions section.
|
|
|
|
|
|
|
| 32 |
|
| 33 |
-
Attribution to the NEWS models:
|
| 34 |
- Chaplynskyi, D. et al. (2021) lang-uk Ukrainian Ubercorpus [Data set]. https://lang.org.ua/uk/corpora/#anchor4
|
|
|
|
| 1 |
---
|
| 2 |
license: cc-by-nc-sa-4.0
|
| 3 |
+
language:
|
| 4 |
+
- uk
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
---
|
| 8 |
|
| 9 |
+
## Community
|
| 10 |
|
| 11 |
+
- Discord: https://discord.gg/yVAjkBgmt4
|
| 12 |
+
- Speech Recognition: https://t.me/speech_recognition_uk
|
| 13 |
+
- Speech Synthesis: https://t.me/speech_synthesis_uk
|
| 14 |
+
- Natural Language Processing: https://t.me/nlp_uk
|
| 15 |
+
|
| 16 |
+
## Overview
|
| 17 |
+
|
| 18 |
+
Different KenLM models for Ukrainian.
|
| 19 |
+
|
| 20 |
+
## Metrics
|
| 21 |
+
|
| 22 |
+
Tested with an acoustic model from [w2v-xls-r-uk](https://huggingface.co/Yehor/w2v-xls-r-uk) model:
|
| 23 |
|
| 24 |
| Model | CER | WER |
|
| 25 |
|-|-|-|
|
|
|
|
| 43 |
| lm-4gram-500k | 0.0247 | 0.1207 |
|
| 44 |
| lm-5gram-500k | 0.0247 | 0.1209 |
|
| 45 |
|
| 46 |
+
Files of the KenLM models are under the Files and versions section.
|
| 47 |
+
|
| 48 |
+
## Attribution
|
| 49 |
|
|
|
|
| 50 |
- Chaplynskyi, D. et al. (2021) lang-uk Ukrainian Ubercorpus [Data set]. https://lang.org.ua/uk/corpora/#anchor4
|