Add model card
Browse files
README.md
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
language: kr
|
| 3 |
+
datasets:
|
| 4 |
+
- aihub 자유대화 음성(노인남녀)
|
| 5 |
+
tags:
|
| 6 |
+
- automatic-speech-recognition
|
| 7 |
+
license: apache-2.0
|
| 8 |
+
---
|
| 9 |
+
|
| 10 |
+
|
| 11 |
+
# wav2vec2-xlsr-korean-senior
|
| 12 |
+
|
| 13 |
+
Futher fine-tuned [fleek/wav2vec-large-xlsr-korean](https://huggingface.co/fleek/wav2vec-large-xlsr-korean) using the [AIhub 자유대화 음성(노인남녀)](https://aihub.or.kr/aidata/30704).
|
| 14 |
+
|
| 15 |
+
- Total train data size: 808,642
|
| 16 |
+
- Total vaild data size: 159,970
|
| 17 |
+
|
| 18 |
+
When using this model, make sure that your speech input is sampled at 16kHz.
|
| 19 |
+
|
| 20 |
+
The script used for training can be found here: https://github.com/hyyoka/wav2vec2-korean-senior
|