This model can perform both verbatim ASR and automatic subtitling. It outputs both modalities with separate decoders. It is trained on Flemish Dutch speech, and should be used with the subtitle branch of the ESPnet toolkit.
Version: September 2023
This model can perform both verbatim ASR and automatic subtitling. It outputs both modalities with separate decoders. It is trained on Flemish Dutch speech, and should be used with the subtitle branch of the ESPnet toolkit.
Version: September 2023