Commit
·
23438b2
1
Parent(s):
429f125
Update README.md
Browse files
README.md
CHANGED
|
@@ -35,9 +35,17 @@ It achieves the following results on the evaluation set:
|
|
| 35 |
- Loss: 0.6007
|
| 36 |
- Wer: 7.9908
|
| 37 |
|
|
|
|
| 38 |
## Model description
|
| 39 |
|
| 40 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 41 |
|
| 42 |
## Intended uses & limitations
|
| 43 |
|
|
|
|
| 35 |
- Loss: 0.6007
|
| 36 |
- Wer: 7.9908
|
| 37 |
|
| 38 |
+
|
| 39 |
## Model description
|
| 40 |
|
| 41 |
+
This model was created as part of the Whisper Fine-Tune Event. This is my first attempt at fine-tuning the Whisper neural network.
|
| 42 |
+
Honestly, it's my second time ever trying anything related to training a neural network, and my first time was pretty bad (but I did
|
| 43 |
+
get a lot of rather funny images out of it, so perhaps it wasn't entirely fruitless?), and it seems like the WER only went up after step 2000,
|
| 44 |
+
so... I'm not sure if I did a good job or if I just wasted GPU cycles, but maybe I can try again and get a better score?
|
| 45 |
+
|
| 46 |
+
I'm learning.
|
| 47 |
+
|
| 48 |
+
|
| 49 |
|
| 50 |
## Intended uses & limitations
|
| 51 |
|