automatic-speech-recognition speech audio CTC Conformer Transformer pytorch NeMo hf-asr-leaderboard Riva

NVIDIA Conformer-CTC Large (be)

<style> img { display: inline; } </style>

| Model architecture | Model size | Language | Riva Compatible |

This model transcribes speech in lowercase Belarusian alphabet including spaces and apostrophes, and is trained on few hundreds of Belarusian speech data. It is a non-autoregressive "large" variant of Conformer, with around 120 million parameters. See the model architecture section and NeMo documentation for complete architecture details. It is also compatible with NVIDIA Riva for production-grade server deployments.

Usage

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.

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']

Automatically instantiate the model

import nemo.collections.asr as nemo_asr
asr_model = nemo_asr.models.EncDecCTCModelBPE.from_pretrained("nvidia/stt_be_conformer_ctc_large")

Transcribing using Python

Simply do:

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

Transcribing many audio files

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

Input

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

Output

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

Model Architecture

Conformer-CTC model is a non-autoregressive variant of Conformer model [1] for Automatic Speech Recognition which uses CTC loss/decoding instead of Transducer. You may find more info on the detail of this model here: Conformer-CTC Model.

Training

The NeMo toolkit [3] was used for training the models for over several 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.

The checkpoint of the language model used as the neural rescorer can be found here. You may find more info on how to train and use language models for ASR models here: ASR Language Modeling

Datasets

All the models in this collection are trained on a composite dataset (NeMo ASRSET) comprising of several hundreds hours of Belarusian speech:

Performance

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

Version Tokenizer Vocabulary Size MCV 10 Test Train Dataset
1.12.0 Google Sentencepiece 1024 4.8 MCV 10

Limitations

Since all models are trained on just academic 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 speech.

Deployment with NVIDIA Riva

For the best real-time accuracy, latency, and throughput, deploy the model with NVIDIA Riva, an accelerated speech AI SDK deployable on-prem, in all clouds, multi-cloud, hybrid, at the edge, and embedded. Additionally, Riva provides:

Check out Riva live demo.

References