Commit
•
cc2451a
1
Parent(s):
c6230d1
End of training
Browse files
README.md
CHANGED
@@ -6,18 +6,18 @@ base_model: tarteel-ai/whisper-base-ar-quran
|
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
-
-
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
-
- name:
|
14 |
results:
|
15 |
- task:
|
16 |
name: Automatic Speech Recognition
|
17 |
type: automatic-speech-recognition
|
18 |
dataset:
|
19 |
name: Zolfa Dataset
|
20 |
-
type:
|
21 |
args: 'config: ar, split: test'
|
22 |
metrics:
|
23 |
- name: Wer
|
@@ -28,11 +28,11 @@ model-index:
|
|
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 |
-
#
|
32 |
|
33 |
This model is a fine-tuned version of [tarteel-ai/whisper-base-ar-quran](https://huggingface.co/tarteel-ai/whisper-base-ar-quran) on the Zolfa Dataset dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
-
- Loss: 0.
|
36 |
- Wer: 10.3448
|
37 |
|
38 |
## Model description
|
@@ -58,23 +58,38 @@ The following hyperparameters were used during training:
|
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
-
-
|
|
|
62 |
- mixed_precision_training: Native AMP
|
63 |
|
64 |
### Training results
|
65 |
|
66 |
-
| Training Loss | Epoch
|
67 |
-
|
68 |
-
| 0.
|
69 |
-
| 0.
|
70 |
-
| 0.
|
71 |
-
| 0.
|
72 |
-
| 0.
|
73 |
-
| 0.
|
74 |
-
| 0.
|
75 |
-
| 0.
|
76 |
-
| 0.
|
77 |
-
| 0.0003 | 10.0
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
78 |
|
79 |
|
80 |
### Framework versions
|
|
|
6 |
tags:
|
7 |
- generated_from_trainer
|
8 |
datasets:
|
9 |
+
- zolfa
|
10 |
metrics:
|
11 |
- wer
|
12 |
model-index:
|
13 |
+
- name: Whisper Small Ar - 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
|
|
|
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 |
+
# Whisper Small Ar - raghadomar
|
32 |
|
33 |
This model is a fine-tuned version of [tarteel-ai/whisper-base-ar-quran](https://huggingface.co/tarteel-ai/whisper-base-ar-quran) on the Zolfa Dataset dataset.
|
34 |
It achieves the following results on the evaluation set:
|
35 |
+
- Loss: 0.0325
|
36 |
- Wer: 10.3448
|
37 |
|
38 |
## Model description
|
|
|
58 |
- seed: 42
|
59 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
60 |
- lr_scheduler_type: linear
|
61 |
+
- lr_scheduler_warmup_steps: 500
|
62 |
+
- training_steps: 500
|
63 |
- mixed_precision_training: Native AMP
|
64 |
|
65 |
### Training results
|
66 |
|
67 |
+
| Training Loss | Epoch | Step | Validation Loss | Wer |
|
68 |
+
|:-------------:|:-------:|:----:|:---------------:|:-------:|
|
69 |
+
| 0.0002 | 1.0 | 21 | 0.0317 | 10.3448 |
|
70 |
+
| 0.0002 | 2.0 | 42 | 0.0287 | 10.3448 |
|
71 |
+
| 0.0001 | 3.0 | 63 | 0.0293 | 10.3448 |
|
72 |
+
| 0.0002 | 4.0 | 84 | 0.0298 | 10.3448 |
|
73 |
+
| 0.0002 | 5.0 | 105 | 0.0281 | 10.3448 |
|
74 |
+
| 0.0002 | 6.0 | 126 | 0.0308 | 10.3448 |
|
75 |
+
| 0.0002 | 7.0 | 147 | 0.0262 | 10.3448 |
|
76 |
+
| 0.0008 | 8.0 | 168 | 0.0341 | 10.3448 |
|
77 |
+
| 0.0002 | 9.0 | 189 | 0.0223 | 3.4483 |
|
78 |
+
| 0.0003 | 10.0 | 210 | 0.0411 | 10.3448 |
|
79 |
+
| 0.0002 | 11.0 | 231 | 0.0357 | 10.3448 |
|
80 |
+
| 0.0003 | 12.0 | 252 | 0.0349 | 10.3448 |
|
81 |
+
| 0.0001 | 13.0 | 273 | 0.0429 | 10.3448 |
|
82 |
+
| 0.0003 | 14.0 | 294 | 0.0311 | 10.3448 |
|
83 |
+
| 0.0003 | 15.0 | 315 | 0.0372 | 10.3448 |
|
84 |
+
| 0.0002 | 16.0 | 336 | 0.0329 | 10.3448 |
|
85 |
+
| 0.0002 | 17.0 | 357 | 0.0390 | 10.3448 |
|
86 |
+
| 0.0004 | 18.0 | 378 | 0.0333 | 10.3448 |
|
87 |
+
| 0.0002 | 19.0 | 399 | 0.0450 | 10.3448 |
|
88 |
+
| 0.0003 | 20.0 | 420 | 0.0384 | 10.3448 |
|
89 |
+
| 0.0002 | 21.0 | 441 | 0.0366 | 10.3448 |
|
90 |
+
| 0.0002 | 22.0 | 462 | 0.0360 | 10.3448 |
|
91 |
+
| 0.0001 | 23.0 | 483 | 0.0441 | 10.3448 |
|
92 |
+
| 0.0006 | 23.8095 | 500 | 0.0325 | 10.3448 |
|
93 |
|
94 |
|
95 |
### Framework versions
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 290403936
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1bccfaae65962ea4e054e62a53803b1e4e208eb9aa81f413ee2b27998e95888d
|
3 |
size 290403936
|
runs/May15_17-04-55_d0b109c9e3e6/events.out.tfevents.1715792707.d0b109c9e3e6.328.1
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2884ef6cbdd97dd698716ebbcd7e91f52f69d3307ee5848690faff3b437792c
|
3 |
+
size 18597
|