mlsanityData to 7 Oct 2026

NeMo: a toolkit for building AI applications using Neural Modules

arXiv 1909.09577 ↗First posted 14 Sep 2019cs.LG cs.CL cs.SDcited by 230

Not on the map. Why?

Abstract (arXiv)

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

Key facts. Cited by 230 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Sep 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 29; 2023: 44; 2024: 53; 2025: 47; 2026: 42.

230 papers.

Sort:

By area:

  1. 2022Robust Speech Recognition via Large-Scale Weak Supervisioncited by 3,972
  2. 2021SpeechBrain: A General-Purpose Speech Toolkitcited by 404
  3. 2022BigVGAN: A Universal Neural Vocoder with Large-Scale Trainingcited by 245
  4. 2024NVILA: Efficient Frontier Visual Language Modelscited by 206
  5. 2023ChipNeMo: Domain-Adapted LLMs for Chip Designcited by 168
  6. 2024OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Datasetcited by 143
  7. 2022Generative Spoken Dialogue Language Modelingcited by 125
  8. 2023Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labelscited by 113
  9. 2023SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHFcited by 107
  10. 2022StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberationcited by 105
  11. 2025HD-EPIC: A Highly-Detailed Egocentric Video Datasetcited by 101
  12. 2021Guided-TTS: A Diffusion Model for Text-to-Speech via Classifier Guidancecited by 84
38 more
  1. 2021SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognitioncited by 77
  2. 2023Zipformer: A faster and better encoder for automatic speech recognitioncited by 77
  3. 2023SALM: Speech-augmented Language Model with In-context Learning for Speech Recognition and Translationcited by 75
  4. 2024EARS: An Anechoic Fullband Speech Dataset Benchmarked for Speech Enhancement and Dereverberationcited by 62
  5. 2023Efficient Sequence Transduction by Jointly Predicting Tokens and Durationscited by 56
  6. 2024Open-Source Conversational AI with SpeechBrain 1.0cited by 55
  7. 2023Privacy-Preserving In-Context Learning for Large Language Modelscited by 50
  8. 2024Upcycling Large Language Models into Mixture of Expertscited by 48
  9. 2024DeSTA2: Developing Instruction-Following Speech Language Model Without Speech Instruction-Tuning Datacited by 43
  10. 2024Flextron: Many-in-One Flexible Large Language Modelcited by 42
  11. 2024NeMo-Aligner: Scalable Toolkit for Efficient Model Alignmentcited by 40
  12. 2022Guided-TTS 2: A Diffusion Model for High-quality Adaptive Text-to-Speech with Untranscribed Datacited by 35
  13. 2022SLUE Phase-2: A Benchmark Suite of Diverse Spoken Language Understanding Taskscited by 34
  14. 2024DeSTA: Enhancing Speech Language Models through Descriptive Speech-Text Alignmentcited by 32
  15. 2025SALM-Duplex: Efficient and Direct Duplex Modeling for Speech-to-Speech Language Modelcited by 32
  16. 2024Benchmarking Children's ASR with Supervised and Self-supervised Speech Foundation Modelscited by 29
  17. 2021NeMo Inverse Text Normalization: From Development To Productioncited by 28
  18. 2024Speech-Copilot: Leveraging Large Language Models for Speech Processing via Task Decomposition, Modularization, and Program Generationcited by 27
  19. 2023nach0: Multimodal Natural and Chemical Languages Foundation Modelcited by 26
  20. 2023FedBPT: Efficient Federated Black-box Prompt Tuning for Large Language Modelscited by 25
  21. 2021ESPnet2-TTS: Extending the Edge of TTS Researchcited by 22
  22. 2022ConvLab-3: A Flexible Dialogue System Toolkit Based on a Unified Data Formatcited by 22
  23. 2023Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictionscited by 22
  24. 2024Benchmarking Large Multimodal Models against Common Corruptionscited by 22
  25. 2024ESPnet-SPK: full pipeline speaker embedding toolkit with reproducible recipes, self-supervised front-ends, and off-the-shelf modelscited by 22
  26. 2024Building a Taiwanese Mandarin Spoken Language Model: A First Attemptcited by 22
  27. 2025Cyber-Zero: Training Cybersecurity Agents without Runtimecited by 22
  28. 2023Vistaar: Diverse Benchmarks and Training Sets for Indian Language ASRcited by 21
  29. 2025Open ASR Leaderboard: Towards Reproducible and Transparent Multilingual and Long-Form Speech Recognition Evaluationcited by 21
  30. 2023Stateful Conformer with Cache-based Inference for Streaming Automatic Speech Recognitioncited by 20
  31. 2025OmniScience: A Domain-Specialized LLM for Scientific Reasoning and Discoverycited by 20
  32. 2022ESB: A Benchmark For Multi-Domain End-to-End Speech Recognitioncited by 18
  33. 2024NOTSOFAR-1 Challenge: New Datasets, Baseline, and Tasks for Distant Meeting Transcriptioncited by 18
  34. 2024BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5cited by 18
  35. 2021CTC Variations Through New WFST Topologiescited by 17
  36. 2022WavThruVec: Latent speech representation as intermediate features for neural speech synthesiscited by 17
  37. 2024Chain-of-Thought Prompting for Speech Translationcited by 17
  38. 2023XPhoneBERT: A Pre-trained Multilingual Model for Phoneme Representations for Text-to-Speechcited by 16

50 most cited of 230 All 230 (JSON)