Commit
·
1cc71b4
1
Parent(s):
e51db1d
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
|
| 2 |
---
|
| 3 |
-
Whisper Small Ar- Martha:
|
| 4 |
|
| 5 |
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
|
| 6 |
|
|
@@ -8,21 +8,21 @@ Loss: 0.5854
|
|
| 8 |
|
| 9 |
Wer: 70.2071
|
| 10 |
|
| 11 |
-
Model description
|
| 12 |
|
| 13 |
More information needed
|
| 14 |
|
| 15 |
-
Intended uses & limitations
|
| 16 |
|
| 17 |
More information needed
|
| 18 |
|
| 19 |
-
Training and evaluation data
|
| 20 |
|
| 21 |
More information needed
|
| 22 |
|
| 23 |
-
Training procedure
|
| 24 |
|
| 25 |
-
Training hyperparameters
|
| 26 |
|
| 27 |
The following hyperparameters were used during training:
|
| 28 |
|
|
@@ -45,20 +45,18 @@ training_steps: 500
|
|
| 45 |
|
| 46 |
mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
-
Training results
|
| 49 |
|
| 50 |
-
Training Loss
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 51 |
|
| 52 |
-
0.9692 0.14 125 1.3372 173.0952
|
| 53 |
|
| 54 |
-
0.5716 0.29 250 0.9058 148.6795
|
| 55 |
|
| 56 |
-
|
| 57 |
-
|
| 58 |
-
0.3083 0.57 500 0.5854 70.2071
|
| 59 |
-
|
| 60 |
-
|
| 61 |
-
Framework versions
|
| 62 |
|
| 63 |
Transformers 4.26.0.dev0
|
| 64 |
|
|
|
|
| 1 |
|
| 2 |
---
|
| 3 |
+
## Whisper Small Ar- Martha:
|
| 4 |
|
| 5 |
This model is a fine-tuned version of openai/whisper-small on the Common Voice 11.0 dataset. It achieves the following results on the evaluation set:
|
| 6 |
|
|
|
|
| 8 |
|
| 9 |
Wer: 70.2071
|
| 10 |
|
| 11 |
+
## Model description
|
| 12 |
|
| 13 |
More information needed
|
| 14 |
|
| 15 |
+
## Intended uses & limitations
|
| 16 |
|
| 17 |
More information needed
|
| 18 |
|
| 19 |
+
## Training and evaluation data
|
| 20 |
|
| 21 |
More information needed
|
| 22 |
|
| 23 |
+
## Training procedure
|
| 24 |
|
| 25 |
+
## Training hyperparameters
|
| 26 |
|
| 27 |
The following hyperparameters were used during training:
|
| 28 |
|
|
|
|
| 45 |
|
| 46 |
mixed_precision_training: Native AMP
|
| 47 |
|
| 48 |
+
# Training results
|
| 49 |
|
| 50 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 51 |
+
|:-------------:|:-----:|:----:|:---------------:|:-------:|
|
| 52 |
+
| 0.9692 | 0.14 | 125 | 1.3372 | 173.0952|
|
| 53 |
+
| 0.5716 | 0.29 | 250 | 0.9058 | 148.6795|
|
| 54 |
+
| 0.3297 | 0.43 | 375 | 0.5825 | 63.6709 |
|
| 55 |
+
| 0.3083 | 0.57 | 500 | 0.5854 | 70.2071 |
|
| 56 |
|
|
|
|
| 57 |
|
|
|
|
| 58 |
|
| 59 |
+
## Framework versions
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 60 |
|
| 61 |
Transformers 4.26.0.dev0
|
| 62 |
|