mikr commited on
Commit
c738b2c
1 Parent(s): a94ee59

update model card README.md

Browse files
Files changed (2) hide show
  1. README.md +12 -9
  2. run.log +11 -0
README.md CHANGED
@@ -1,38 +1,41 @@
1
  ---
 
 
2
  license: apache-2.0
3
  tags:
 
4
  - generated_from_trainer
5
  datasets:
6
- - common_voice_11_0
7
  metrics:
8
  - wer
9
  model-index:
10
- - name: openai/whisper-large-v2
11
  results:
12
  - task:
13
  name: Automatic Speech Recognition
14
  type: automatic-speech-recognition
15
  dataset:
16
- name: common_voice_11_0
17
- type: common_voice_11_0
18
  config: cs
19
  split: test
20
  args: cs
21
  metrics:
22
  - name: Wer
23
  type: wer
24
- value: 8.473140457818456
25
  ---
26
 
27
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
28
  should probably proofread and complete it, then remove this comment. -->
29
 
30
- # openai/whisper-large-v2
31
 
32
- This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the common_voice_11_0 dataset.
33
  It achieves the following results on the evaluation set:
34
- - Loss: 0.2913
35
- - Wer: 8.4731
36
 
37
  ## Model description
38
 
 
1
  ---
2
+ language:
3
+ - cs
4
  license: apache-2.0
5
  tags:
6
+ - whisper-event
7
  - generated_from_trainer
8
  datasets:
9
+ - mozilla-foundation/common_voice_11_0
10
  metrics:
11
  - wer
12
  model-index:
13
+ - name: Whisper Large-v2 Czech CV11 v2
14
  results:
15
  - task:
16
  name: Automatic Speech Recognition
17
  type: automatic-speech-recognition
18
  dataset:
19
+ name: mozilla-foundation/common_voice_11_0 cs
20
+ type: mozilla-foundation/common_voice_11_0
21
  config: cs
22
  split: test
23
  args: cs
24
  metrics:
25
  - name: Wer
26
  type: wer
27
+ value: 8.37737794884072
28
  ---
29
 
30
  <!-- This model card has been generated automatically according to the information the Trainer had access to. You
31
  should probably proofread and complete it, then remove this comment. -->
32
 
33
+ # Whisper Large-v2 Czech CV11 v2
34
 
35
+ This model is a fine-tuned version of [openai/whisper-large-v2](https://huggingface.co/openai/whisper-large-v2) on the mozilla-foundation/common_voice_11_0 cs dataset.
36
  It achieves the following results on the evaluation set:
37
+ - Loss: 0.2563
38
+ - Wer: 8.3774
39
 
40
  ## Model description
41
 
run.log CHANGED
@@ -40336,3 +40336,14 @@ To https://huggingface.co/mikr/whisper-audio-concat-test
40336
  [INFO|configuration_utils.py:447] 2022-12-21 04:15:55,920 >> Configuration saved in ./config.json
40337
  [INFO|modeling_utils.py:1680] 2022-12-21 04:16:00,242 >> Model weights saved in ./pytorch_model.bin
40338
  [INFO|feature_extraction_utils.py:368] 2022-12-21 04:16:00,258 >> Feature extractor saved in ./preprocessor_config.json
 
 
 
 
 
 
 
 
 
 
 
 
40336
  [INFO|configuration_utils.py:447] 2022-12-21 04:15:55,920 >> Configuration saved in ./config.json
40337
  [INFO|modeling_utils.py:1680] 2022-12-21 04:16:00,242 >> Model weights saved in ./pytorch_model.bin
40338
  [INFO|feature_extraction_utils.py:368] 2022-12-21 04:16:00,258 >> Feature extractor saved in ./preprocessor_config.json
40339
+
40340
+ remote: LFS file scan complete.
40341
+ To https://huggingface.co/mikr/whisper-audio-concat-test
40342
+ 77bae23..a94ee59 main -> main
40343
+
40344
+ 12/21/2022 04:17:44 - WARNING - huggingface_hub.repository - remote: Scanning LFS files for validity, may be slow...
40345
+ remote: LFS file scan complete.
40346
+ To https://huggingface.co/mikr/whisper-audio-concat-test
40347
+ 77bae23..a94ee59 main -> main
40348
+
40349
+