NeLF Project

Welcome to the official HuggingFace page of the NeLF Project: Next Level Flemish Speech Processing.

On this page, you can find all the state-of-the-art Flemish Dutch speech models that have been created by researchers of KU Leuven and UGent as part of the NeLF project.

For more information about NeLF and the research, visit our website.

Models

We host several models, which are specifically tailored to the processing of Flemish Dutch speech. Further details and instructions for usage of the models can be found in the respective repositories.

Automatic Speech Recognition (ASR)

-- ASR_subtitles_v2 (Recommended): The second version of our Automatic Speech Recognition and Subtitle Generation model, with improved architecture and trained on 14000 hours of Flemish broadcast subtitled speech data. It can generate both an exact verbatim transcription with annotation tags as well as a fully formatted and cleaned up subtitle transcription.

-- ASR_subtitles_v2_small: Smaller variant of ASR_subtitles_v2 with almost as good performance.

-- ASR_subtitles_v1: The first version of the ASR and Subtitling model trained on 1000 hours of Flemish data.

-- ASR_verbatim_v1: The first version of the ASR and Subtitling model trained on 1000 hours of Flemish data, converted to a verbatim-only ASR model.

-- Whisper: A finetuned Whisper Large model on Flemish data can be found here. Usage instructions can be found in Whisper documentation.

USAGE: To use our ASR models and transcribe speech yourself, use our codebase.

Speaker Diarization and Identification

-- ecapa2_diarization: Will be added shortly.

Leaderboard

Word Error Rates on different test sets.