Ru3ll commited on
Commit
bd3917a
1 Parent(s): 3e9290b

update model card README.md

Browse files
Files changed (1) hide show
  1. README.md +10 -7
README.md CHANGED
@@ -1,22 +1,25 @@
1
  ---
 
 
2
  tags:
 
3
  - generated_from_trainer
4
  datasets:
5
- - afrispeech-200
6
  metrics:
7
  - wer
8
  model-index:
9
- - name: dsn_afrispeech-shuffle
10
  results:
11
  - task:
12
  name: Automatic Speech Recognition
13
  type: automatic-speech-recognition
14
  dataset:
15
- name: afrispeech-200
16
- type: afrispeech-200
17
  config: all
18
  split: train
19
- args: all
20
  metrics:
21
  - name: Wer
22
  type: wer
@@ -26,9 +29,9 @@ model-index:
26
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
27
  should probably proofread and complete it, then remove this comment. -->
28
 
29
- # dsn_afrispeech-shuffle
30
 
31
- This model is a fine-tuned version of [Ru3ll/dsn_afrispeech4](https://huggingface.co/Ru3ll/dsn_afrispeech4) on the afrispeech-200 dataset.
32
  It achieves the following results on the evaluation set:
33
  - Loss: 0.6337
34
  - Wer: 27.0411
 
1
  ---
2
+ language:
3
+ - en
4
  tags:
5
+ - hf-asr-leaderboard
6
  - generated_from_trainer
7
  datasets:
8
+ - tobiolatunji/afrispeech-200
9
  metrics:
10
  - wer
11
  model-index:
12
+ - name: Ru3ll/dsn_afrispeech3
13
  results:
14
  - task:
15
  name: Automatic Speech Recognition
16
  type: automatic-speech-recognition
17
  dataset:
18
+ name: Afrispeech-200
19
+ type: tobiolatunji/afrispeech-200
20
  config: all
21
  split: train
22
+ args: 'config: en, split: test'
23
  metrics:
24
  - name: Wer
25
  type: wer
 
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
+ # Ru3ll/dsn_afrispeech3
33
 
34
+ This model is a fine-tuned version of [ru3ll/dsn_afrispeech2/whisper-small](https://huggingface.co/ru3ll/dsn_afrispeech2/whisper-small) on the Afrispeech-200 dataset.
35
  It achieves the following results on the evaluation set:
36
  - Loss: 0.6337
37
  - Wer: 27.0411