DigitalUmuganda/mbaza_noise_robust_asr_rw_v1

Model Overview

<DESCRIBE IN ONE LINE THE MODEL AND ITS USE>

Dependencies

To train, fine-tune or play with the model you will need to install NVIDIA NeMo.

For inference just run:

pip install nemo_toolkit['all']

How to Use this Model

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

Load the model weights

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.ASRModel.from_pretrained("DigitalUmuganda/mbaza_noise_robust_asr_rw_v1")

Transcribing using Python

asr_model.transcribe(['<audio_sample>'])

Transcribing many audio files

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

Input

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