Hugging Face's logo

Spaces:
WebashalarForML
/
SpacyModelCreator
Sleeping

App Files Community
1
WebashalarForML commited on
Commit
6a272a1
·
verified ·
1 Parent(s): 4bac692

Update templates/guide.html

Browse files
Files changed (1) hide show
  1. templates/guide.html +172 -167
templates/guide.html CHANGED
@@ -1,167 +1,172 @@
1
- <!DOCTYPE html>
2
- <html lang="en">
3
- <head>
4
- <meta charset="UTF-8" />
5
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
6
- <title>SpaCy NER Training Guide</title>
7
- <link
8
- rel="stylesheet"
9
- href="https://maxcdn.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css"
10
- />
11
- <style>
12
- body {
13
- background-color: #121212;
14
- font-family: "Poppins", sans-serif;
15
- color: #e0e0e0;
16
- margin: 0;
17
- padding: 0;
18
- }
19
- h1,
20
- h2 {
21
- color: #007bff;
22
- }
23
- .step {
24
- margin-bottom: 30px;
25
- border: 1px solid #007bff;
26
- border-radius: 5px;
27
- padding: 20px;
28
- background-color: #1e1e1e;
29
- }
30
- .btn-primary {
31
- color: #fff;
32
- background-color: #007bff;
33
- border: 1px solid #007bff;
34
- }
35
- .btn-primary:hover {
36
- background-color: transparent;
37
- border: 1px solid #007bff;
38
- }
39
- </style>
40
- </head>
41
- <body>
42
- <div class="container">
43
- <h1>SpaCy NER Model Training Guide</h1>
44
-
45
- <div class="step">
46
- <h2>Step 1: Upload Your Resume File</h2>
47
- <p>
48
- Upload a resume or document file for text extraction. Supported
49
- formats include:
50
- </p>
51
- <ul>
52
- <li>PDF</li>
53
- <li>DOCX (Word Document)</li>
54
- <li>RSF (Rich Structured Format)</li>
55
- <li>ODT (Open Document Text)</li>
56
- <li>PNG, JPG, JPEG (Image Formats)</li>
57
- <li>JSON</li>
58
- </ul>
59
- <p>
60
- Ensure that your file is in one of the supported formats before
61
- uploading. The system will extract and process the text from your
62
- document automatically.
63
- </p>
64
- <a href="{{ url_for('index') }}" class="btn btn-primary"
65
- >Proceed to Upload</a
66
- >
67
- </div>
68
-
69
- <div class="step">
70
- <h2>Step 2: Preview and Edit Extracted Text</h2>
71
- <p>
72
- After uploading your document, you will be shown a preview of the
73
- extracted text. This preview allows you to edit the text if needed to
74
- correct any extraction errors or remove unwanted content. Once you're
75
- satisfied, click "Next" to proceed to Named Entity Recognition (NER)
76
- annotations.
77
- </p>
78
- <a href="{{ url_for('text_preview') }}" class="btn btn-primary"
79
- >Proceed to Text Preview</a
80
- >
81
- </div>
82
-
83
- <div class="step">
84
- <h2>Step 3: Annotate Named Entities</h2>
85
- <p>
86
- In this step, you will preview the Named Entity Recognition (NER)
87
- results generated from your text. You can add new entity labels,
88
- select relevant text for each label, and make manual adjustments. Once
89
- you’ve annotated the text with the appropriate labels, save your
90
- annotations and export the data in JSON format for model training.
91
- </p>
92
- <p>Instructions:</p>
93
- <ul>
94
- <li>Click "Begin!" to load the extracted text.</li>
95
- <li>
96
- Highlight sections of the text and assign them to the available
97
- labels.
98
- </li>
99
- <li>Add new labels if necessary.</li>
100
- <li>
101
- Once done, click "Export" to download your annotations as a JSON
102
- file.
103
- </li>
104
- </ul>
105
- <a href="{{ url_for('ner_preview') }}" class="btn btn-primary"
106
- >Proceed to NER Annotation</a
107
- >
108
- </div>
109
-
110
- <div class="step">
111
- <h2>Step 4: Save and Format JSON Data</h2>
112
- <p>
113
- Upload your annotated JSON file from the previous step. The system
114
- will process and reformat the JSON file to ensure compatibility with
115
- the SpaCy model training process. After formatting, you can proceed to
116
- the model training step.
117
- </p>
118
- <p>Instructions:</p>
119
- <ul>
120
- <li>
121
- Upload the JSON file you downloaded after the annotation step.
122
- </li>
123
- <li>Click "Process" to reformat the file.</li>
124
- <li>
125
- Once processing is complete, click "Next" to proceed with training.
126
- </li>
127
- </ul>
128
- <a href="{{ url_for('json_file') }}" class="btn btn-primary"
129
- >Proceed to Save JSON</a
130
- >
131
- </div>
132
-
133
- <div class="step">
134
- <h2>Step 5: Train the NER Model</h2>
135
- <p>
136
- In this final step, you will convert the formatted JSON data into the
137
- SpaCy format and begin training the NER model. You can customize the
138
- training by selecting the number of epochs (iterations) the model will
139
- go through and setting the version for the trained model.
140
- </p>
141
- <p>Guidelines:</p>
142
- <ul>
143
- <li>
144
- Number of epochs: The higher the number of epochs, the more times
145
- the model will learn from the data, but too many epochs can lead to
146
- overfitting. Start with 10 epochs for a balanced training approach.
147
- </li>
148
- <li>
149
- Model versioning: Provide a version name for this training session,
150
- so you can keep track of different versions of the model.
151
- </li>
152
- </ul>
153
- <p>
154
- Once the training is complete, you can download the latest version of
155
- the trained model for use in production.
156
- </p>
157
- <a href="{{ url_for('spacy_file') }}" class="btn btn-primary"
158
- >Proceed to Model Training</a
159
- >
160
- </div>
161
- </div>
162
-
163
- <script src="https://code.jquery.com/jquery-3.5.1.slim.min.js"></script>
164
- <script src="https://cdn.jsdelivr.net/npm/@popperjs/core@2.11.6/dist/umd/popper.min.js"></script>
165
- <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js"></script>
166
- </body>
167
- </html>
 
 
 
 
 
 
1
+ <!DOCTYPE html>
2
+ <html lang="en">
3
+ <head>
4
+ <meta charset="UTF-8" />
5
+ <meta name="viewport" content="width=device-width, initial-scale=1.0" />
6
+ <title>SpaCy NER Training Guide</title>
7
+ <link
8
+ rel="stylesheet"
9
+ href="https://maxcdn.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css"
10
+ />
11
+ <style>
12
+ body {
13
+ background-color: #121212;
14
+ font-family: "Poppins", sans-serif;
15
+ color: #e0e0e0;
16
+ margin: 0;
17
+ padding: 0;
18
+ }
19
+ h1,
20
+ h2 {
21
+ color: #007bff;
22
+ }
23
+ .step {
24
+ margin-bottom: 30px;
25
+ border: 1px solid #007bff;
26
+ border-radius: 5px;
27
+ padding: 20px;
28
+ background-color: #1e1e1e;
29
+ }
30
+ .btn-primary {
31
+ color: #fff;
32
+ background-color: #007bff;
33
+ border: 1px solid #007bff;
34
+ }
35
+ .btn-primary:hover {
36
+ background-color: transparent;
37
+ border: 1px solid #007bff;
38
+ }
39
+ </style>
40
+ </head>
41
+ <body>
42
+ <div class="container">
43
+ <h1>SpaCy NER Model Training Guide</h1>
44
+
45
+ <div class="step">
46
+ <h2>Step 1: Upload Your Resume File</h2>
47
+ <p>
48
+ Upload a resume or document file for text extraction. Supported
49
+ formats include:
50
+ </p>
51
+ <ul>
52
+ <li>PDF</li>
53
+ <li>DOCX (Word Document)</li>
54
+ <li>RSF (Rich Structured Format)</li>
55
+ <li>ODT (Open Document Text)</li>
56
+ <li>PNG, JPG, JPEG (Image Formats)</li>
57
+ <li>JSON</li>
58
+ </ul>
59
+ <p>
60
+ Ensure that your file is in one of the supported formats before
61
+ uploading. The system will extract and process the text from your
62
+ document automatically.
63
+ </p>
64
+ <a href="{{ url_for('index') }}" class="btn btn-primary"
65
+ >Proceed to Upload</a
66
+ >
67
+ </div>
68
+
69
+ <div class="step">
70
+ <h2>Step 2: Preview and Edit Extracted Text</h2>
71
+ <p>
72
+ After uploading your document, you will be shown a preview of the
73
+ extracted text. This preview allows you to edit the text if needed to
74
+ correct any extraction errors or remove unwanted content. Once you're
75
+ satisfied, click "Next" to proceed to Named Entity Recognition (NER)
76
+ annotations.
77
+ </p>
78
+ <a href="{{ url_for('text_preview') }}" class="btn btn-primary"
79
+ >Proceed to Text Preview</a
80
+ >
81
+ </div>
82
+
83
+ <div class="step">
84
+ <h2>Step 3: Annotate Named Entities</h2>
85
+ <p>
86
+ In this step, you will preview the Named Entity Recognition (NER)
87
+ results generated from your text. You can add new entity labels,
88
+ select relevant text for each label, and make manual adjustments. Once
89
+ you’ve annotated the text with the appropriate labels, save your
90
+ annotations and export the data in JSON format for model training.
91
+ NOTE:(following labels can be taken in use: ["ABOUT","CERTIFICATE",
92
+ "COMPANY","CONTACT","COURSE", "DOB", "EMAIL", "EXPERIENCE", "HOBBIES",
93
+ "INSTITUTE", "JOB_TITLE", "LANGUAGE", "LAST_QUALIFICATION_YEAR", "LINK",
94
+ "LOCATION", "PERSON", "PROJECTS", "QUALIFICATION", "SCHOOL", "SKILL",
95
+ "SOFT_SKILL", "UNIVERSITY", "YEARS_EXPERIENCE"]
96
+ </p>
97
+ <p>Instructions:</p>
98
+ <ul>
99
+ <li>Click "Begin!" to load the extracted text.</li>
100
+ <li>
101
+ Highlight sections of the text and assign them to the available
102
+ labels.
103
+ </li>
104
+ <li>Add new labels if necessary.</li>
105
+ <li>
106
+ Once done, click "Export" to download your annotations as a JSON
107
+ file.
108
+ </li>
109
+ </ul>
110
+ <a href="{{ url_for('ner_preview') }}" class="btn btn-primary"
111
+ >Proceed to NER Annotation</a
112
+ >
113
+ </div>
114
+
115
+ <div class="step">
116
+ <h2>Step 4: Save and Format JSON Data</h2>
117
+ <p>
118
+ Upload your annotated JSON file from the previous step. The system
119
+ will process and reformat the JSON file to ensure compatibility with
120
+ the SpaCy model training process. After formatting, you can proceed to
121
+ the model training step.
122
+ </p>
123
+ <p>Instructions:</p>
124
+ <ul>
125
+ <li>
126
+ Upload the JSON file you downloaded after the annotation step.
127
+ </li>
128
+ <li>Click "Process" to reformat the file.</li>
129
+ <li>
130
+ Once processing is complete, click "Next" to proceed with training.
131
+ </li>
132
+ </ul>
133
+ <a href="{{ url_for('json_file') }}" class="btn btn-primary"
134
+ >Proceed to Save JSON</a
135
+ >
136
+ </div>
137
+
138
+ <div class="step">
139
+ <h2>Step 5: Train the NER Model</h2>
140
+ <p>
141
+ In this final step, you will convert the formatted JSON data into the
142
+ SpaCy format and begin training the NER model. You can customize the
143
+ training by selecting the number of epochs (iterations) the model will
144
+ go through and setting the version for the trained model.
145
+ </p>
146
+ <p>Guidelines:</p>
147
+ <ul>
148
+ <li>
149
+ Number of epochs: The higher the number of epochs, the more times
150
+ the model will learn from the data, but too many epochs can lead to
151
+ overfitting. Start with 10 epochs for a balanced training approach.
152
+ </li>
153
+ <li>
154
+ Model versioning: Provide a version name for this training session,
155
+ so you can keep track of different versions of the model.
156
+ </li>
157
+ </ul>
158
+ <p>
159
+ Once the training is complete, you can download the latest version of
160
+ the trained model for use in production.
161
+ </p>
162
+ <a href="{{ url_for('spacy_file') }}" class="btn btn-primary"
163
+ >Proceed to Model Training</a
164
+ >
165
+ </div>
166
+ </div>
167
+
168
+ <script src="https://code.jquery.com/jquery-3.5.1.slim.min.js"></script>
169
+ <script src="https://cdn.jsdelivr.net/npm/@popperjs/core@2.11.6/dist/umd/popper.min.js"></script>
170
+ <script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js"></script>
171
+ </body>
172
+ </html>