Commit
·
399c972
1
Parent(s):
29a8690
Update README.md
Browse files
README.md
CHANGED
|
@@ -14,7 +14,7 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 14 |
|
| 15 |
# KalemaTech-Arabic-STT-ASR-based-on-Whisper-Small
|
| 16 |
|
| 17 |
-
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.5362
|
| 20 |
- Wer: 58.5848
|
|
@@ -29,7 +29,11 @@ More information needed
|
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
|
| 32 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
|
| 34 |
## Training procedure
|
| 35 |
|
|
|
|
| 14 |
|
| 15 |
# KalemaTech-Arabic-STT-ASR-based-on-Whisper-Small
|
| 16 |
|
| 17 |
+
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on Common_Voice_Arabic_12.0_Augmented.
|
| 18 |
It achieves the following results on the evaluation set:
|
| 19 |
- Loss: 0.5362
|
| 20 |
- Wer: 58.5848
|
|
|
|
| 29 |
|
| 30 |
## Training and evaluation data
|
| 31 |
|
| 32 |
+
Common_Voice_Arabic_12.0 and I made some augmentations to it as follows:
|
| 33 |
+
- 25% of the data TimeMasking
|
| 34 |
+
- 25% of the data SpecAugmentation
|
| 35 |
+
- 25% of the data WavAugmentation (AddGaussianNoise)
|
| 36 |
+
- The final dataset is the original common voice plus the augmented files
|
| 37 |
|
| 38 |
## Training procedure
|
| 39 |
|