Dean Hans Felandio Setiadi Saputra commited on
Update README.md
Browse files
README.md
CHANGED
|
@@ -37,21 +37,8 @@ It achieves the following results on the evaluation set:
|
|
| 37 |
- Loss: 0.5505
|
| 38 |
- Wer: 31.4346
|
| 39 |
|
| 40 |
-
This model is part of my school project, it uses shuffled 100k rows of train dataset since the computation power is limited
|
| 41 |
-
|
| 42 |
-
## Model description
|
| 43 |
-
|
| 44 |
-
More information needed
|
| 45 |
-
|
| 46 |
-
## Intended uses & limitations
|
| 47 |
-
|
| 48 |
-
More information needed
|
| 49 |
-
|
| 50 |
-
## Training and evaluation data
|
| 51 |
-
|
| 52 |
-
More information needed
|
| 53 |
-
|
| 54 |
-
## Training procedure
|
| 55 |
|
| 56 |
### Training hyperparameters
|
| 57 |
|
|
@@ -82,3 +69,17 @@ The following hyperparameters were used during training:
|
|
| 82 |
- Pytorch 2.3.0
|
| 83 |
- Datasets 2.19.1
|
| 84 |
- Tokenizers 0.19.1
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
- Loss: 0.5505
|
| 38 |
- Wer: 31.4346
|
| 39 |
|
| 40 |
+
This model is part of my school project, it uses shuffled 100k rows of train dataset since the computation power is limited.
|
| 41 |
+
Additional information can be found in this github: [HanCreation/Whisper-Tiny-German](https://github.com/HanCreation/Whisper-Tiny-German)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
|
| 43 |
### Training hyperparameters
|
| 44 |
|
|
|
|
| 69 |
- Pytorch 2.3.0
|
| 70 |
- Datasets 2.19.1
|
| 71 |
- Tokenizers 0.19.1
|
| 72 |
+
|
| 73 |
+
## Model description
|
| 74 |
+
|
| 75 |
+
More information needed
|
| 76 |
+
|
| 77 |
+
## Intended uses & limitations
|
| 78 |
+
|
| 79 |
+
More information needed
|
| 80 |
+
|
| 81 |
+
## Training and evaluation data
|
| 82 |
+
|
| 83 |
+
More information needed
|
| 84 |
+
|
| 85 |
+
## Training procedure
|