End of training
Browse files- README.md +36 -4
- model.safetensors +1 -1
README.md
CHANGED
|
@@ -2,22 +2,38 @@
|
|
| 2 |
language:
|
| 3 |
- ar
|
| 4 |
license: apache-2.0
|
|
|
|
| 5 |
tags:
|
| 6 |
- generated_from_trainer
|
| 7 |
-
base_model: openai/whisper-small
|
| 8 |
datasets:
|
| 9 |
- zolfa
|
|
|
|
|
|
|
| 10 |
model-index:
|
| 11 |
-
- name:
|
| 12 |
-
results:
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
---
|
| 14 |
|
| 15 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 16 |
should probably proofread and complete it, then remove this comment. -->
|
| 17 |
|
| 18 |
-
#
|
| 19 |
|
| 20 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Zolfa Dataset dataset.
|
|
|
|
|
|
|
|
|
|
| 21 |
|
| 22 |
## Model description
|
| 23 |
|
|
@@ -46,6 +62,22 @@ The following hyperparameters were used during training:
|
|
| 46 |
- training_steps: 1000
|
| 47 |
- mixed_precision_training: Native AMP
|
| 48 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 49 |
### Framework versions
|
| 50 |
|
| 51 |
- Transformers 4.41.2
|
|
|
|
| 2 |
language:
|
| 3 |
- ar
|
| 4 |
license: apache-2.0
|
| 5 |
+
base_model: openai/whisper-small
|
| 6 |
tags:
|
| 7 |
- generated_from_trainer
|
|
|
|
| 8 |
datasets:
|
| 9 |
- zolfa
|
| 10 |
+
metrics:
|
| 11 |
+
- wer
|
| 12 |
model-index:
|
| 13 |
+
- name: Zolfa-raghadomar
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
name: Automatic Speech Recognition
|
| 17 |
+
type: automatic-speech-recognition
|
| 18 |
+
dataset:
|
| 19 |
+
name: Zolfa Dataset
|
| 20 |
+
type: zolfa
|
| 21 |
+
args: 'config: ar, split: test'
|
| 22 |
+
metrics:
|
| 23 |
+
- name: Wer
|
| 24 |
+
type: wer
|
| 25 |
+
value: 46.42857142857143
|
| 26 |
---
|
| 27 |
|
| 28 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 29 |
should probably proofread and complete it, then remove this comment. -->
|
| 30 |
|
| 31 |
+
# Zolfa-raghadomar
|
| 32 |
|
| 33 |
This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Zolfa Dataset dataset.
|
| 34 |
+
It achieves the following results on the evaluation set:
|
| 35 |
+
- Loss: 0.6824
|
| 36 |
+
- Wer: 46.4286
|
| 37 |
|
| 38 |
## Model description
|
| 39 |
|
|
|
|
| 62 |
- training_steps: 1000
|
| 63 |
- mixed_precision_training: Native AMP
|
| 64 |
|
| 65 |
+
### Training results
|
| 66 |
+
|
| 67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
| 68 |
+
|:-------------:|:------:|:----:|:---------------:|:-------:|
|
| 69 |
+
| 0.041 | 0.6711 | 100 | 0.5255 | 46.4286 |
|
| 70 |
+
| 0.018 | 1.3423 | 200 | 0.5604 | 46.4286 |
|
| 71 |
+
| 0.0166 | 2.0134 | 300 | 0.5781 | 46.4286 |
|
| 72 |
+
| 0.0071 | 2.6846 | 400 | 0.6184 | 46.4286 |
|
| 73 |
+
| 0.0043 | 3.3557 | 500 | 0.6433 | 46.4286 |
|
| 74 |
+
| 0.0024 | 4.0268 | 600 | 0.6825 | 46.4286 |
|
| 75 |
+
| 0.0005 | 4.6980 | 700 | 0.6668 | 46.4286 |
|
| 76 |
+
| 0.0019 | 5.3691 | 800 | 0.6726 | 42.8571 |
|
| 77 |
+
| 0.0005 | 6.0403 | 900 | 0.6859 | 46.4286 |
|
| 78 |
+
| 0.0002 | 6.7114 | 1000 | 0.6824 | 46.4286 |
|
| 79 |
+
|
| 80 |
+
|
| 81 |
### Framework versions
|
| 82 |
|
| 83 |
- Transformers 4.41.2
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 966995080
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b070d129f0e9cc6a62bde2386f9a7fcc987affbfb3093e7663b4d1a0ab99394
|
| 3 |
size 966995080
|