lelapa/fast-conformer-xl-isizulu-v2

Fast-conformer-xl-isizulu-v1

| |

Put a short model description here.

See the model architecture section and NeMo documentation for complete architecture details.

NVIDIA NeMo: Training

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

from nemo.collections.asr.models.ctc_bpe_models import EncDecCTCModelBPE
model = EncDecCTCModelBPE.from_pretrained("lelapa/fast-conformer-xl-isizulu-v1")

Transcribing using Python

First, let's get a sample

wget https://dldata-public.s3.us-east-2.amazonaws.com/2086-149220-0033.wav

Then simply do:

asr_model.transcribe(['2086-149220-0033.wav'])

Transcribing many audio files

python [NEMO_GIT_FOLDER]/examples/asr/transcribe_speech.py      pretrained_name="lelapa/fast-conformer-xl-isizulu-v1"      audio_dir=""

Model Architecture

FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling. The model is trained using CTC loss. You may find more information on the details of FastConformer here: Fast-Conformer Model.

Training

The NeMo toolkit [2] was used for training the models for over 300 hundred epochs. These model are trained 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

This dataset was used to train the model

Performance

Dataet	wer	cer
codeswitcheval	69.56	62.23

License

License to use this model is covered by the CC-BY-4.0. By downloading the public and release version of the model, you accept the terms and conditions of the CC-BY-4.0 license.

References

Provide appropriate references in the markdown link format below. Please order them numerically. [1]Fast Conformer [2]NVIDIA NeMo Toolkit