Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,14 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
This model is a fine-tune of OpenAI's Whisper Large v3 Turbo model (https://huggingface.co/openai/whisper-large-v3-turbo) over the following Korean datasets:
|
| 5 |
+
|
| 6 |
+
https://huggingface.co/datasets/Junhoee/STT_Korean_Dataset_80000
|
| 7 |
+
https://huggingface.co/datasets/Bingsu/zeroth-korean
|
| 8 |
+
Combined they have roughly 102k sentences.
|
| 9 |
+
|
| 10 |
+
This is the last checkpoint which has achieved ~16 WER (down from ~24 WER).
|
| 11 |
+
|
| 12 |
+
Training was 10,000 iterations.
|
| 13 |
+
|
| 14 |
+
The machines for training this model were generously donated by AWS (IVS team).
|