Bekhouche commited on
Commit
51361fe
·
verified ·
1 Parent(s): 2827926

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +13 -10
README.md CHANGED
@@ -4,7 +4,7 @@ emoji: 📈
4
  colorFrom: blue
5
  colorTo: red
6
  sdk: gradio
7
- sdk_version: 3.0.2
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
@@ -13,14 +13,17 @@ tags:
13
  - metric
14
  short_description: Normalized Edit Distance (NED)
15
  description: >-
16
- The Normalized Edit Distance (NED) is a metric used to quantify the dissimilarity between two sequences, typically strings, by measuring the minimum number of editing operations required to transform one sequence into the other, normalized by the length of the longer sequence.
17
- The NED ranges from 0 to 1, where 0 indicates identical sequences and 1 indicates completely dissimilar sequences.
18
- It is particularly useful in tasks such as spell checking, speech recognition, and OCR. The normalized edit distance can be calculated using the formula:
19
- NED = (1 - (ED(pred, gt) / max(length(pred), length(gt))))
20
- Where:
21
- gt: ground-truth sequence
22
- pred: predicted sequence
23
- ED: Edit Distance, the minimum number of editing operations (insertions, deletions, substitutions) needed to transform one sequence into the other.
 
 
 
24
  ---
25
  # Metric Card for NED
26
 
@@ -38,4 +41,4 @@ gt: ground-truth sequence
38
 
39
  pred: predicted sequence
40
 
41
- ED: Edit Distance, the minimum number of editing operations (insertions, deletions, substitutions) needed to transform one sequence into the other.
 
4
  colorFrom: blue
5
  colorTo: red
6
  sdk: gradio
7
+ sdk_version: 4.44.0
8
  app_file: app.py
9
  pinned: false
10
  license: apache-2.0
 
13
  - metric
14
  short_description: Normalized Edit Distance (NED)
15
  description: >-
16
+ The Normalized Edit Distance (NED) is a metric used to quantify the
17
+ dissimilarity between two sequences, typically strings, by measuring the
18
+ minimum number of editing operations required to transform one sequence into
19
+ the other, normalized by the length of the longer sequence. The NED ranges
20
+ from 0 to 1, where 0 indicates identical sequences and 1 indicates completely
21
+ dissimilar sequences. It is particularly useful in tasks such as spell
22
+ checking, speech recognition, and OCR. The normalized edit distance can be
23
+ calculated using the formula: NED = (1 - (ED(pred, gt) / max(length(pred),
24
+ length(gt)))) Where: gt: ground-truth sequence pred: predicted sequence ED:
25
+ Edit Distance, the minimum number of editing operations (insertions,
26
+ deletions, substitutions) needed to transform one sequence into the other.
27
  ---
28
  # Metric Card for NED
29
 
 
41
 
42
  pred: predicted sequence
43
 
44
+ ED: Edit Distance, the minimum number of editing operations (insertions, deletions, substitutions) needed to transform one sequence into the other.