What is the purpose of a dictionary and how does it work?
Enhancing AI Accuracy with Custom Dictionaries
Purpose of a dictionary:
A dictionary helps improve AI's ability to recognise and transcribe words that are not part of its standard training. AI models are typically trained on general data, which means they may struggle to accurately transcribe unique names, specialised vocabulary, or industry-specific terms.
By adding words to a custom dictionary, you expand the AI's 'knowledge' to fit your specific use case. When the AI encounters a word it doesn't recognise, it will consult the dictionary and look for close matches, improving transcription accuracy.
How a Dictionary Works:
- Generic AI Models: Standard AI models are trained on common, everyday language.
- Unrecognized Words: When the AI encounters a word it doesn’t know, such as unique names or technical jargon, it may misinterpret it and give out the closest match.
- Custom Dictionary: A dictionary allows you to add specific terms, so the AI can reference them when it detects unfamiliar words, improving the accuracy of speech-to-text recognition in your particular field.
Note:
Use a custom dictionary when your content contains names, industry jargon or specialised terms that may not be part of the AI's general training data.
How to create a Dictionary:
-
Access the Dictionary Tool:
- From the Workflow Menu, select Dictionaries & Glossaries.
- Click Create Dictionary.
-
Name and Safe your dictionary:
-
Enter a Dictionary Name in the provided field.
-
Click Save to confirm.
-
-
Add Individual Words:
-
Click Add Word to add a new entry.
-
In the Word field, enter how the word should appear in the transcript.
-
In the Sounds Like field, enter the phonetic spelling of how the word is pronounced (see description below).
-
Press Enter to save the word.
-
Batch Import Multiple Words:
- Create a dictionary by following the steps outlined above.
-
Open the Import Option:
-
Click the three dots (⋯) next to the Add Word button.
-
Select Import CSV from the dropdown menu.
-
-
Upload a CSV File:
-
Choose a CSV file from your device.
-
Ensure the file meets the required formatting guidelines before uploading.
-
-
Add Words:
- All words from the CSV file will be automatically imported and added to the dictionary.
Info: CSV Formatting Requirements
A CSV (Comma-Separated Values) file is a simple text file where each entry appears on its own line. This format allows you to quickly add multiple words to your dictionary at once and can be created or edited using common tools such as Excel or Word.
Updated Format with “Sounds Like” Support
To support the Sounds Like feature, your CSV file must follow this structure:
-
Start with the dictionary word
-
Separate the word from its phonetic entries using a semicolon (;)
-
Add one or more Sounds Like entries, separated by commas (,)
Example:
CEO;C.E.O.,see-E-oh
SOC 2;Sock2,Sock-2
This ensures that both the word and its pronunciation variations are imported correctly in a single step.
Note:
Make sure you don't exceed six words for each dictionary item and its 'Sounds Like' entries combined! The system will ignore them.