Using Limecraft Flow you can automatically transcribe audio into timed text. Using 'Custom Dictionaries', you can reduce the Word Error Rate (WER) by half and save as much time during post-editing. In this article, we explain how to configure and use custom dictionaries to achieve maximum efficiency.
1. Configuring a dictionary
Before starting an automatic transcription with a custom dictionary, we first need to configure it.
To do that, go to your Production Settings and then to the Transciber. This page has a section called 'Dictionaries', as seen below.
Note that if this 'Dictionaries' section is not available in the Transcriber settings page, then your production might be configured with a transcription engine that does not support dictionaries.
To create a new dictionary, click the ‘Add new dictionary’ button.<
Clicking the ‘Add new dictionary’ button will give you the following screen:
Start by filling in a descriptive name for the dictionary. You can also select a language and a domain for your dictionary, but this is optional.
Next type in (or copy/paste) the dictionary entries in the large input field at the bottom of the page. A dictionary entry can be a single word, but it can also be a phrase which you expect to appear as-is in the spoken text of your material.
Each line in this input field should contain a single dictionary entry. You can specify up to 1000 entries in your dictionary.
Once you typed in all the dictionary entries, hit ‘Save dictionary’. You should see a green message saying your changes were saved successfully.
If you navigate back to the Transcriber settings page, you’ll now see a table containing one row for the dictionary you just created.
On the right side of the dictionary row, there is a … menu which allows you to edit, remove or export the dictionary.
2. Exporting / importing a dictionary
On the page where you edit a dictionary, you have the option to export the dictionary itself and to import dictionary terms.
2.1 Exporting a dictionary
You can export a dictionary as a JSON file or as a CSV (comma separated value) file. The latter can be useful when working with spreadsheet software. In all other cases, we advise to use the JSON format.
2.2 Importing a dictionary
A dictionary that was exported can be imported again (on the same or on another production). Simply select the file, and choose if you would like to replace all entries that are already in the dictionary or not.
When importing a CSV dictionary file that was not exported by Limecraft:
To avoid issues though, it is best to start from a CSV exported from a Limecraft dictionary, and edit that.
3. Automatic transcription with a dictionary
If you want to start an automatic transcription with a dictionary, open the transcriber for the clip as shown below.
Select a language which has support for automatic transcription. Under ‘how would you like to start?’, you can select the option to convert clip audio to transcript.
At the bottom of the page, the ‘Use Dictionary’ section becomes available. Select the dictionary we just created ("Famous actors").
Start the automatic transcription by clicking ‘Convert audio to text’.
4. Automatic subtitling with a dictionary
The dictionary option is also available when using automatic transcription to generate subtitles in the subtitle editor.