librarian-bot commited on
Commit
2caa823
1 Parent(s): a737878

Librarian Bot: Add base_model information to model

Browse files

This pull request aims to enrich the metadata of your model by adding [`openai/whisper-large-v2`](https://huggingface.co/openai/whisper-large-v2) as a `base_model` field, situated in the `YAML` block of your model's `README.md`.

How did we find this information? We performed a regular expression match on your `README.md` file to determine the connection.

**Why add this?** Enhancing your model's metadata in this way:
- **Boosts Discoverability** - It becomes straightforward to trace the relationships between various models on the Hugging Face Hub.
- **Highlights Impact** - It showcases the contributions and influences different models have within the community.

For a hands-on example of how such metadata can play a pivotal role in mapping model connections, take a look at [librarian-bots/base_model_explorer](https://huggingface.co/spaces/librarian-bots/base_model_explorer).

This PR comes courtesy of [Librarian Bot](https://huggingface.co/librarian-bot). If you have any feedback, queries, or need assistance, please don't hesitate to reach out to [@davanstrien](https://huggingface.co/davanstrien). Your input is invaluable to us!

Files changed (1) hide show
  1. README.md +28 -28
README.md CHANGED
@@ -1,8 +1,7 @@
1
  ---
2
- license: apache-2.0
3
  language: fr
 
4
  library_name: transformers
5
- thumbnail: null
6
  tags:
7
  - automatic-speech-recognition
8
  - hf-asr-leaderboard
@@ -11,12 +10,13 @@ datasets:
11
  - mozilla-foundation/common_voice_11_0
12
  metrics:
13
  - wer
 
14
  model-index:
15
  - name: Fine-tuned whisper-large-v2 model for ASR in French
16
  results:
17
  - task:
18
- name: Automatic Speech Recognition
19
  type: automatic-speech-recognition
 
20
  dataset:
21
  name: Common Voice 11.0
22
  type: mozilla-foundation/common_voice_11_0
@@ -24,15 +24,15 @@ model-index:
24
  split: test
25
  args: fr
26
  metrics:
27
- - name: WER (Greedy)
28
- type: wer
29
  value: 8.05
30
- - name: WER (Beam 5)
31
- type: wer
32
  value: 7.67
 
33
  - task:
34
- name: Automatic Speech Recognition
35
  type: automatic-speech-recognition
 
36
  dataset:
37
  name: Multilingual LibriSpeech (MLS)
38
  type: facebook/multilingual_librispeech
@@ -40,15 +40,15 @@ model-index:
40
  split: test
41
  args: french
42
  metrics:
43
- - name: WER (Greedy)
44
- type: wer
45
  value: 5.56
46
- - name: WER (Beam 5)
47
- type: wer
48
  value: 5.28
 
49
  - task:
50
- name: Automatic Speech Recognition
51
  type: automatic-speech-recognition
 
52
  dataset:
53
  name: VoxPopuli
54
  type: facebook/voxpopuli
@@ -56,15 +56,15 @@ model-index:
56
  split: test
57
  args: fr
58
  metrics:
59
- - name: WER (Greedy)
60
- type: wer
61
- value: 11.50
62
- - name: WER (Beam 5)
63
- type: wer
64
  value: 10.69
 
65
  - task:
66
- name: Automatic Speech Recognition
67
  type: automatic-speech-recognition
 
68
  dataset:
69
  name: Fleurs
70
  type: google/fleurs
@@ -72,15 +72,15 @@ model-index:
72
  split: test
73
  args: fr_fr
74
  metrics:
75
- - name: WER (Greedy)
76
- type: wer
77
  value: 5.42
78
- - name: WER (Beam 5)
79
- type: wer
80
  value: 5.05
 
81
  - task:
82
- name: Automatic Speech Recognition
83
  type: automatic-speech-recognition
 
84
  dataset:
85
  name: African Accented French
86
  type: gigant/african_accented_french
@@ -88,12 +88,12 @@ model-index:
88
  split: test
89
  args: fr
90
  metrics:
91
- - name: WER (Greedy)
92
- type: wer
93
  value: 6.47
94
- - name: WER (Beam 5)
95
- type: wer
96
  value: 5.95
 
97
  ---
98
 
99
  <style>
 
1
  ---
 
2
  language: fr
3
+ license: apache-2.0
4
  library_name: transformers
 
5
  tags:
6
  - automatic-speech-recognition
7
  - hf-asr-leaderboard
 
10
  - mozilla-foundation/common_voice_11_0
11
  metrics:
12
  - wer
13
+ base_model: openai/whisper-large-v2
14
  model-index:
15
  - name: Fine-tuned whisper-large-v2 model for ASR in French
16
  results:
17
  - task:
 
18
  type: automatic-speech-recognition
19
+ name: Automatic Speech Recognition
20
  dataset:
21
  name: Common Voice 11.0
22
  type: mozilla-foundation/common_voice_11_0
 
24
  split: test
25
  args: fr
26
  metrics:
27
+ - type: wer
 
28
  value: 8.05
29
+ name: WER (Greedy)
30
+ - type: wer
31
  value: 7.67
32
+ name: WER (Beam 5)
33
  - task:
 
34
  type: automatic-speech-recognition
35
+ name: Automatic Speech Recognition
36
  dataset:
37
  name: Multilingual LibriSpeech (MLS)
38
  type: facebook/multilingual_librispeech
 
40
  split: test
41
  args: french
42
  metrics:
43
+ - type: wer
 
44
  value: 5.56
45
+ name: WER (Greedy)
46
+ - type: wer
47
  value: 5.28
48
+ name: WER (Beam 5)
49
  - task:
 
50
  type: automatic-speech-recognition
51
+ name: Automatic Speech Recognition
52
  dataset:
53
  name: VoxPopuli
54
  type: facebook/voxpopuli
 
56
  split: test
57
  args: fr
58
  metrics:
59
+ - type: wer
60
+ value: 11.5
61
+ name: WER (Greedy)
62
+ - type: wer
 
63
  value: 10.69
64
+ name: WER (Beam 5)
65
  - task:
 
66
  type: automatic-speech-recognition
67
+ name: Automatic Speech Recognition
68
  dataset:
69
  name: Fleurs
70
  type: google/fleurs
 
72
  split: test
73
  args: fr_fr
74
  metrics:
75
+ - type: wer
 
76
  value: 5.42
77
+ name: WER (Greedy)
78
+ - type: wer
79
  value: 5.05
80
+ name: WER (Beam 5)
81
  - task:
 
82
  type: automatic-speech-recognition
83
+ name: Automatic Speech Recognition
84
  dataset:
85
  name: African Accented French
86
  type: gigant/african_accented_french
 
88
  split: test
89
  args: fr
90
  metrics:
91
+ - type: wer
 
92
  value: 6.47
93
+ name: WER (Greedy)
94
+ - type: wer
95
  value: 5.95
96
+ name: WER (Beam 5)
97
  ---
98
 
99
  <style>