To train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest Pytorch version.

pip install nemo_toolkit['all']

How to Use this Model

The model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset.

Automatically instantiate the model

python

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.ASRModel.from_pretrained("iqbalc/stt_de_conformer_transducer_large")

Transcribing using Python

asr_model.transcribe(['filename.wav'])

Transcribing many audio files

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py  pretrained_name="iqbalc/stt_de_conformer_transducer_large"  audio_dir="<DIRECTORY CONTAINING AUDIO FILES>"

Input

This model accepts 16000 KHz Mono-channel Audio (wav files) as input.

Output

This model provides transcribed speech as a string for a given audio sample.

Model Architecture

Conformer-Transducer model is an autoregressive variant of Conformer model for Automatic Speech Recognition which uses Transducer loss/decoding

Training

The NeMo toolkit was used for training the models. These models are fine-tuned with this example script and this base config.

The tokenizers for these models were built using the text transcripts of the train set with this script.

Datasets

All the models in this collection are trained on a composite dataset comprising of over two thousand hours of cleaned German speech:

MCV7.0 567 hours
MLS 1524 hours
VoxPopuli 214 hours

Performance

Performances of the ASR models are reported in terms of Word Error Rate (WER%) with greedy decoding.

MCV7.0 test = 4.93

Limitations

The model might perform worse for accented speech

References

NVIDIA NeMo Toolkit