Before using the service, please read the preliminary information containing a description of steps that enable access to the CLARIN-PL developer interface.
A service for automatic splitting of an audio file by speaker. The service is available only for the English language.
The diaryzation model comes from NVIDIA/NeMo. The service takes an audio file, performs diaryzation and translation to text on it. This is a subtask performed by Whisper.
It can be useful, for example, in research that requires the transcription of recordings.
Diaryzator can be run by using an LPMN query in the LPMN Client service:
The service can be run in the Windows system with default values using the following LPMN query: ['diarizer'].
No parameters.
An audio file in .wav or .mp3 format.
A json file containing the transcription of the sound and the division of the fragments into speakers.
Performance of the service for longer files to be tested.
In Colab: Diaryzator - Splitting of an audio file by speaker
(C) CLARIN-PL