Hugging Face's logo

deepdml
/
whisper-base-ar-mix-norm

Automatic Speech Recognition
Transformers
TensorBoard
Safetensors
Arabic
whisper
Generated from Trainer
Eval Results (legacy)
Model card Files
xet
 Metrics Community
deepdml commited on
Commit
d5e840a
·
1 Parent(s): bfd4fa7

End of training

Browse files
Files changed (1) hide show
  1. README.md +14 -11
README.md CHANGED
@@ -6,6 +6,9 @@ base_model: openai/whisper-base
6
  tags:
7
  - generated_from_trainer
8
  datasets:
 
 
 
9
  - mozilla-foundation/common_voice_17_0
10
  metrics:
11
  - wer
@@ -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: 37.278505934634644
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-base](https://huggingface.co/openai/whisper-base) on the Common Voice 17.0 dataset.
36
  It achieves the following results on the evaluation set:
37
- - Loss: 2.6641
38
- - Wer: 37.2785
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
- | 0.313 | 0.2 | 1000 | 2.1696 | 43.1981 |
71
- | 0.1558 | 1.0454 | 2000 | 2.4420 | 39.4273 |
72
- | 0.0949 | 1.2454 | 3000 | 2.5789 | 37.7829 |
73
- | 0.0701 | 2.0908 | 4000 | 2.6314 | 37.1904 |
74
- | 0.0465 | 2.2908 | 5000 | 2.6641 | 37.2785 |
75
 
76
 
77
  ### Framework versions
 
6
  tags:
7
  - generated_from_trainer
8
  datasets:
9
+ - UBC-NLP/Casablanca
10
+ - google/fleurs
11
+ - ymoslem/MediaSpeech
12
  - mozilla-foundation/common_voice_17_0
13
  metrics:
14
  - wer
 
20
  type: automatic-speech-recognition
21
  dataset:
22
  name: Common Voice 17.0
23
+ type: UBC-NLP/Casablanca
24
  config: ar
25
  split: test
26
  args: ar
27
  metrics:
28
  - name: Wer
29
  type: wer
30
+ value: 60.7676585850631
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-base](https://huggingface.co/openai/whisper-base) on the Common Voice 17.0 dataset.
39
  It achieves the following results on the evaluation set:
40
+ - Loss: 2.6739
41
+ - Wer: 60.7677
42
 
43
  ## Model description
44
 
 
68
 
69
  ### Training results
70
 
71
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
72
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
73
+ | 0.6127 | 0.2 | 1000 | 2.1392 | 51.3435 |
74
+ | 0.3365 | 0.4 | 2000 | 2.4225 | 48.5384 |
75
+ | 0.2029 | 0.6 | 3000 | 2.5954 | 50.8035 |
76
+ | 0.1403 | 0.8 | 4000 | 2.7056 | 53.3236 |
77
+ | 0.1053 | 1.0 | 5000 | 2.6739 | 60.7677 |
78
 
79
 
80
  ### Framework versions