TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Speech Recognition	Common Voice French	ConformerCTC-L (4-gram)	Test WER	9.16%	# 2
Speech Recognition	Common Voice French	ConformerCTC-L (no-LM)	Test WER	9.63%	# 4
Speech Recognition	Common Voice German	ConformerCTC-L (4-gram)	Test WER	6.03%	# 5
Speech Recognition	Common Voice German	ConformerCTC-L (no LM)	Test WER	6.68%	# 9
Speech Recognition	Common Voice Spanish	ConformerCTC-L (4-gram)	Test WER	5.5%	# 1
Speech Recognition	Common Voice Spanish	ConformerCTC-L (no LM)	Test WER	6.9%	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/nemo-a-toolkit-for-building-ai-applications/speech-recognition-on-common-voice-spanish)](https://paperswithcode.com/sota/speech-recognition-on-common-voice-spanish?p=nemo-a-toolkit-for-building-ai-applications)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/nemo-a-toolkit-for-building-ai-applications/speech-recognition-on-common-voice-french)](https://paperswithcode.com/sota/speech-recognition-on-common-voice-french?p=nemo-a-toolkit-for-building-ai-applications)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/nemo-a-toolkit-for-building-ai-applications/speech-recognition-on-common-voice-german)](https://paperswithcode.com/sota/speech-recognition-on-common-voice-german?p=nemo-a-toolkit-for-building-ai-applications)`

NeMo: a toolkit for building AI applications using Neural Modules

14 Sep 2019 · Oleksii Kuchaiev, Jason Li, Huyen Nguyen, Oleksii Hrinchuk, Ryan Leary, Boris Ginsburg, Samuel Kriman, Stanislav Beliaev, Vitaly Lavrukhin, Jack Cook, Patrice Castonguay, Mariya Popova, Jocelyn Huang, Jonathan M. Cohen ·

NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition. NeMo is built around neural modules, conceptual blocks of neural networks that take typed inputs and produce typed outputs. Such modules typically represent data layers, encoders, decoders, language models, loss functions, or methods of combining activations. NeMo makes it easy to combine and re-use these building blocks while providing a level of semantic correctness checking via its neural type system. The toolkit comes with extendable collections of pre-built modules for automatic speech recognition and natural language processing. Furthermore, NeMo provides built-in support for distributed training and mixed precision on latest NVIDIA GPUs. NeMo is open-source https://github.com/NVIDIA/NeMo

PDF Abstract

Code

Add Remove Mark official

NVIDIA/NeMo

9,997

Tasks

Add Remove

Automatic Speech Recognition

Automatic Speech Recognition (ASR)

speech-recognition

Speech Recognition

Datasets

Common Voice

Results from the Paper

Edit

Ranked #1 on Speech Recognition on Common Voice Spanish (using extra training data)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Speech Recognition	Common Voice French	ConformerCTC-L (4-gram)	Test WER	9.16%	# 2	Compare
Speech Recognition	Common Voice French	ConformerCTC-L (no-LM)	Test WER	9.63%	# 4	Compare
Speech Recognition	Common Voice German	ConformerCTC-L (4-gram)	Test WER	6.03%	# 5	Compare
Speech Recognition	Common Voice German	ConformerCTC-L (no LM)	Test WER	6.68%	# 9	Compare
Speech Recognition	Common Voice Spanish	ConformerCTC-L (4-gram)	Test WER	5.5%	# 1	Compare
Speech Recognition	Common Voice Spanish	ConformerCTC-L (no LM)	Test WER	6.9%	# 4	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

NeMo: a toolkit for building AI applications using Neural Modules

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove