|
2 | 2 | Scripts for processing audio and images |
3 | 3 |
|
4 | 4 | #### [dhashImageComparison.py](dhashImageComparison.py) |
5 | | -Based on user input, this script creates dhashes for all of the image files in the specified directory and then compares them using a BK-tree and creates a CSV file of all dhashes matches that are below the specified threshold (e.g. '40' means the dhashes are 40% different and 60% similar). |
| 5 | +Based on user input, creates dhashes for all of the image files in the specified directory and then compares them using a BK-tree and creates a CSV file of all dhashes matches that are below the specified threshold (e.g. '40' means the dhashes are 40% different and 60% similar). |
6 | 6 |
|
7 | 7 | #### [ocrDirectoryOfImages.py](ocrDirectoryOfImages.py) |
8 | | -Based on user input, this script generates an optical character recognition text file for all of the jpgs in a specified directory. |
| 8 | +Based on user input, generates an optical character recognition text file for all of the jpgs in a specified directory. |
9 | 9 |
|
10 | 10 | #### [stringComparisonFromCSV.py](stringComparisonFromCSV.py) |
11 | | -Based on a specified file and a specified threshold (e.g. '90' means the strings are 90% similar and 10% different), the script compares each string against every other string in the file, identifies all strings with a similarity above the specified threshold, and prints it to a new CSV file. |
| 11 | +Based on a specified file and a specified threshold (e.g. '90' means the strings are 90% similar and 10% different), compares each string against every other string in the file, identifies all strings with a similarity above the specified threshold, and prints it to a new CSV file. |
12 | 12 |
|
13 | 13 | #### [stringComparisonFromCSVOldAndNew.py](stringComparisonFromCSVOldAndNew.py) |
14 | | -Based on a specified files of new and old strings and a specified threshold (e.g. '90' means the strings are 90% similar and 10% different), the script compares each string against every other string in the new strings file, identifies all strings with a similarity above the specified threshold, and prints it to a new CSV file. It also compares each string to a CSV file of old strings that have previously received an authorized form (e.g. adding new name headings to an existing authority file) |
| 14 | +Based on a specified files of new and old strings and a specified threshold (e.g. '90' means the strings are 90% similar and 10% different), compares each string against every other string in the new strings file, identifies all strings with a similarity above the specified threshold, and prints it to a new CSV file. It also compares each string to a CSV file of old strings that have previously received an authorized form (e.g. adding new name headings to an existing authority file) |
15 | 15 |
|
16 | 16 | #### [transcribeAudioFile.py](transcribeAudioFile.py) |
17 | | -This script generates a rough, unformatted transcript of a specified MP3 using the free Wit ([https://wit.ai/](https://wit.ai/)) speech-to-text API. The script requires a secrets.py file in the same directory that must contain the following text: |
| 17 | +Generates a rough, unformatted transcript of a specified MP3 using the free Wit ([https://wit.ai/](https://wit.ai/)) speech-to-text API. The script requires a secrets.py file in the same directory that must contain the following text: |
18 | 18 | ``` |
19 | 19 | filePath ='[The file path where the source MP3]' |
20 | 20 | witKey ='[The 'Server Access Token' on the 'Settings' page from your Wit.ai account]' |
|
0 commit comments