Hugging Face's logo

deepdml
/
whisper-medium-ar-mix-norm

TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Eval Results
Model card Files
xet
Metrics Community
deepdml commited on
Commit
6faf00a
·
verified ·
1 Parent(s): 6b39cb2

End of training

Browse files
Files changed (3) hide show
  1. README.md +14 -11
  2. model.safetensors +1 -1
  3. runs/Sep14_04-33-32_7cd27b3a0909/events.out.tfevents.1757824415.7cd27b3a0909.694.0 +2 -2
README.md CHANGED
@@ -6,7 +6,10 @@ base_model: openai/whisper-medium
6
  tags:
7
  - generated_from_trainer
8
  datasets:
 
 
9
  - mozilla-foundation/common_voice_17_0
 
10
  metrics:
11
  - wer
12
  model-index:
@@ -17,14 +20,14 @@ model-index:
17
  type: automatic-speech-recognition
18
  dataset:
19
  name: Common Voice 17.0
20
- type: mozilla-foundation/common_voice_17_0
21
  config: ar
22
  split: test
23
  args: ar
24
  metrics:
25
  - name: Wer
26
  type: wer
27
- value: 13.026194896026702
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -34,8 +37,8 @@ should probably proofread and complete it, then remove this comment. -->
34
 
35
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 2.4605
38
- - Wer: 13.0262
39
 
40
  ## Model description
41
 
@@ -65,13 +68,13 @@ The following hyperparameters were used during training:
65
 
66
  ### Training results
67
 
68
- | Training Loss | Epoch | Step | Validation Loss | Wer |
69
- |:-------------:|:------:|:----:|:---------------:|:-------:|
70
- | 0.0936 | 0.2 | 1000 | 2.0372 | 17.0951 |
71
- | 0.0498 | 0.4 | 2000 | 2.2405 | 15.5107 |
72
- | 0.0262 | 0.6 | 3000 | 2.2643 | 14.4681 |
73
- | 0.0289 | 1.0908 | 4000 | 2.3300 | 13.2568 |
74
- | 0.0246 | 1.2908 | 5000 | 2.4605 | 13.0262 |
75
 
76
 
77
  ### Framework versions
 
6
  tags:
7
  - generated_from_trainer
8
  datasets:
9
+ - ymoslem/MediaSpeech
10
+ - UBC-NLP/Casablanca
11
  - mozilla-foundation/common_voice_17_0
12
+ - google/fleurs
13
  metrics:
14
  - wer
15
  model-index:
 
20
  type: automatic-speech-recognition
21
  dataset:
22
  name: Common Voice 17.0
23
+ type: ymoslem/MediaSpeech
24
  config: ar
25
  split: test
26
  args: ar
27
  metrics:
28
  - name: Wer
29
  type: wer
30
+ value: 15.325045470739346
31
  ---
32
 
33
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 
37
 
38
  This model is a fine-tuned version of [openai/whisper-medium](https://huggingface.co/openai/whisper-medium) on the Common Voice 17.0 dataset.
39
  It achieves the following results on the evaluation set:
40
+ - Loss: 2.4504
41
+ - Wer: 15.3250
42
 
43
  ## Model description
44
 
 
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
73
+ | 0.2423 | 0.2 | 1000 | 2.0205 | 21.3178 |
74
+ | 0.0667 | 0.4 | 2000 | 2.3750 | 18.2033 |
75
+ | 0.047 | 0.6 | 3000 | 2.4276 | 17.5658 |
76
+ | 0.0249 | 0.8 | 4000 | 2.7231 | 16.1576 |
77
+ | 0.017 | 1.0 | 5000 | 2.4504 | 15.3250 |
78
 
79
 
80
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:91cf93b2782c1324e9f0a497b59de069b4c391f60c8865c15e5e0c9e4c3d2e54
3
  size 3055544304
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:989e206181a51f1a7587f0c86bed4fa5366f915c5c9c3127113ccb8407c0da86
3
  size 3055544304
runs/Sep14_04-33-32_7cd27b3a0909/events.out.tfevents.1757824415.7cd27b3a0909.694.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:392fdb7d1af519024b3ae78d06e247b6b5fb910d1f0d5c196a3cf6dd71496de6
3
- size 41655
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0418a05401b3a7c0b7def6242bcfcbb82de08ef2866416069f9b8399d806d0ff
3
+ size 50767