Hugging Face's logo

zeroMN
/
auto

Question Answering
Transformers
English
Chinese
multimodal
vqa
text
audio
Eval Results
Model card Files
xet
Community
zeroMN commited on
Commit
6f44c08
·
verified ·
1 Parent(s): 1581cbd

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +43 -47
README.md CHANGED
@@ -3,7 +3,7 @@ language:
3
  - en
4
  - zh
5
  license: apache-2.0
6
- library_name: transformers
7
  tags:
8
  - multimodal
9
  - vqa
@@ -28,53 +28,49 @@ model-index:
28
  metrics:
29
  - type: accuracy
30
  value: 85
31
- pipeline_tag: any-to-any
32
-
33
  model_index:
34
- - name: AutoModel
35
- results:
36
- - task:
37
- type: vqa # 支持视觉问答任务
38
- name: Visual Question Answering
39
- dataset:
40
- type: synthetdataset
41
- name: Synthetic Multimodal Dataset
42
- config: default
43
- split: test
44
- revision: main
45
- metrics:
46
- - type: accuracy
47
- value: 85.0
48
- name: VQA Accuracy
49
- - task:
50
- type: automatspeerecognition
51
- name: Automatic Speech Recognition
52
- dataset:
53
- type: synthetdataset
54
- name: Synthetic Multimodal Dataset
55
- config: default
56
- split: test
57
- revision: main
58
- metrics:
59
- - type: wer
60
- value: 15.3
61
- name: Test WER
62
- - task:
63
- type: captioning
64
- name: Image Captioning
65
- dataset:
66
- type: synthetdataset
67
- name: Synthetic Multimodal Dataset
68
- config: default
69
- split: test
70
- revision: main
71
- metrics:
72
- - type: bleu
73
- value: 27.5
74
- name: BL4
75
-
76
-
77
-
78
  ---
79
  ### **3. 提供可下载文件**
80
  确保以下文件已上传到仓库，便于用户下载和运行：
 
3
  - en
4
  - zh
5
  license: apache-2.0
6
+ library_name: transformers
7
  tags:
8
  - multimodal
9
  - vqa
 
28
  metrics:
29
  - type: accuracy
30
  value: 85
31
+ pipeline_tag: question-answering
 
32
  model_index:
33
+ - name: AutoModel
34
+ results:
35
+ - task:
36
+ type: vqa
37
+ name: Visual Question Answering
38
+ dataset:
39
+ type: synthetdataset
40
+ name: Synthetic Multimodal Dataset
41
+ config: default
42
+ split: test
43
+ revision: main
44
+ metrics:
45
+ - type: accuracy
46
+ value: 85
47
+ name: VQA Accuracy
48
+ - task:
49
+ type: automatspeerecognition
50
+ name: Automatic Speech Recognition
51
+ dataset:
52
+ type: synthetdataset
53
+ name: Synthetic Multimodal Dataset
54
+ config: default
55
+ split: test
56
+ revision: main
57
+ metrics:
58
+ - type: wer
59
+ value: 15.3
60
+ name: Test WER
61
+ - task:
62
+ type: captioning
63
+ name: Image Captioning
64
+ dataset:
65
+ type: synthetdataset
66
+ name: Synthetic Multimodal Dataset
67
+ config: default
68
+ split: test
69
+ revision: main
70
+ metrics:
71
+ - type: bleu
72
+ value: 27.5
73
+ name: BL4
 
 
 
74
  ---
75
  ### **3. 提供可下载文件**
76
  确保以下文件已上传到仓库，便于用户下载和运行：