Model Overview The model contains large size versions of Conformer-Transducer (around 120M parameters) trained on German NeMo ASRSet with over 2000 hours of speech. The model transcribes speech in lower case German alphabet along with spaces but without punctuation.
Architecture Conformer-Transducer model is an autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses Transducer loss/decoding
Dataset The model trained has been trained on a composite dataset (NeMo ASRSET) comprising of over two thousand hours of cleaned German speech: MCV7.0 567 hours MLS 1524 hours VoxPopuli 214 hours
Input This model accepts 16000 KHz Mono-channel Audio (wav files) as input
Limitations Since this model was trained on publically available speech datasets, the performance of this model might degrade for speech which includes technical terms, or vernacular that the model has not been trained on. The model might also perform worse for accented speec