humeur commited on
Commit
98fd040
1 Parent(s): 0db7791

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +32 -5
README.md CHANGED
@@ -1,23 +1,40 @@
1
  ---
2
  language:
3
- - sv
4
  license: apache-2.0
5
  tags:
6
  - hf-asr-leaderboard
7
  - generated_from_trainer
8
  datasets:
9
- - mozilla-foundati/common_voice_11_0
 
 
10
  model-index:
11
- - name: Whisper Small sv-SE to en
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
- # Whisper Small sv-SE to en
19
 
20
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
 
 
 
21
 
22
  ## Model description
23
 
@@ -46,6 +63,16 @@ The following hyperparameters were used during training:
46
  - training_steps: 4000
47
  - mixed_precision_training: Native AMP
48
 
 
 
 
 
 
 
 
 
 
 
49
  ### Framework versions
50
 
51
  - Transformers 4.26.0.dev0
 
1
  ---
2
  language:
3
+ - se
4
  license: apache-2.0
5
  tags:
6
  - hf-asr-leaderboard
7
  - generated_from_trainer
8
  datasets:
9
+ - mozilla-foundation/common_voice_11_0
10
+ metrics:
11
+ - wer
12
  model-index:
13
+ - name: Whisper Small sv-SE - KTH
14
+ results:
15
+ - task:
16
+ name: Automatic Speech Recognition
17
+ type: automatic-speech-recognition
18
+ dataset:
19
+ name: Common Voice 11.0
20
+ type: mozilla-foundation/common_voice_11_0
21
+ config: sv
22
+ split: test
23
+ metrics:
24
+ - name: Wer
25
+ type: wer
26
+ value: 19.11929903392496
27
  ---
28
 
29
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
30
  should probably proofread and complete it, then remove this comment. -->
31
 
32
+ # Whisper Small sv-SE - KTH
33
 
34
  This model is a fine-tuned version of [openai/whisper-small](https://huggingface.co/openai/whisper-small) on the Common Voice 11.0 dataset.
35
+ It achieves the following results on the evaluation set:
36
+ - Loss: 0.3310
37
+ - Wer: 19.1193
38
 
39
  ## Model description
40
 
 
63
  - training_steps: 4000
64
  - mixed_precision_training: Native AMP
65
 
66
+ ### Training results
67
+
68
+ | Training Loss | Epoch | Step | Validation Loss | Wer |
69
+ |:-------------:|:-----:|:----:|:---------------:|:-------:|
70
+ | 0.1015 | 1.29 | 1000 | 0.2880 | 20.4134 |
71
+ | 0.0387 | 2.59 | 2000 | 0.2959 | 19.6810 |
72
+ | 0.0126 | 3.88 | 3000 | 0.3103 | 19.2990 |
73
+ | 0.0035 | 5.17 | 4000 | 0.3310 | 19.1193 |
74
+
75
+
76
  ### Framework versions
77
 
78
  - Transformers 4.26.0.dev0