Search Results for author:
Found 30 papers, 13 papers with code
NVIDIA NeMo Offline Speech Translation Systems for IWSLT 2022
Our cascade system consists of 1) Conformer RNN-T automatic speech recognition model, 2) punctuation-capitalization model based on pre-trained T5 encoder, 3) ensemble of Transformer neural machine translation models fine-tuned on TED talks.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+5
NVIDIA NeMo’s Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21
This paper provides an overview of NVIDIA NeMo’s neural machine translation systems for the constrained data track of the WMT21 News and Biomedical Shared Translation Tasks.
Llama-Nemotron: Efficient Reasoning Models
We introduce the Llama-Nemotron series of models, an open family of heterogeneous reasoning models that deliver exceptional reasoning capabilities, inference efficiency, and an open license for enterprise use.
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
We introduce Nemotron-H, a family of 8B and 56B/47B hybrid Mamba-Transformer models designed to reduce inference cost for a given accuracy level.
HelpSteer2-Preference: Complementing Ratings with Preferences
Reward models are critical for aligning models to follow instructions, and are typically trained following one of two popular paradigms: Bradley-Terry style or Regression style.
LLM Pruning and Distillation in Practice: The Minitron Approach
We present a comprehensive report on compressing the Llama 3. 1 8B and Mistral NeMo 12B models to 4B and 8B parameters, respectively, using pruning and distillation.
GPT vs RETRO: Exploring the Intersection of Retrieval and Parameter-Efficient Fine-Tuning
Parameter-Efficient Fine-Tuning (PEFT) and Retrieval-Augmented Generation (RAG) have become popular methods for adapting large language models while minimizing compute requirements.
Nemotron-4 340B Technical Report
We release the Nemotron-4 340B model family, including Nemotron-4-340B-Base, Nemotron-4-340B-Instruct, and Nemotron-4-340B-Reward.
HelpSteer2: Open-source dataset for training top-performing reward models
Using a powerful internal base model trained on HelpSteer2, we are able to achieve the SOTA score (92. 0%) on Reward-Bench's primary dataset, outperforming currently listed open and proprietary models, as of June 12th, 2024.
NeMo-Aligner: Scalable Toolkit for Efficient Model Alignment
Aligning Large Language Models (LLMs) with human values and preferences is essential for making them helpful and safe.
Nemotron-4 15B Technical Report
We introduce Nemotron-4 15B, a 15-billion-parameter large multilingual language model trained on 8 trillion text tokens.
HelpSteer: Multi-attribute Helpfulness Dataset for SteerLM
To alleviate this problem, we collect HelpSteer, a multi-attribute helpfulness dataset annotated for the various aspects that make responses helpful.
Tied-Lora: Enhancing parameter efficiency of LoRA with weight tying
We introduce Tied-LoRA, a novel paradigm leveraging weight tying and selective training to enhance the parameter efficiency of Low-rank Adaptation (LoRA).
SteerLM: Attribute Conditioned SFT as an (User-Steerable) Alternative to RLHF
Model alignment with human preferences is an essential step in making Large Language Models (LLMs) helpful and consistent with human values.
Leveraging Synthetic Targets for Machine Translation
In this work, we provide a recipe for training machine translation models in a limited resource setting by leveraging synthetic target data generated using a large pre-trained model.
Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study
Thus, it is still an open question: shall we pretrain large autoregressive LMs with retrieval?
Finding the Right Recipe for Low Resource Domain Adaptation in Neural Machine Translation
General translation models often still struggle to generate accurate translations in specialized domains.
NVIDIA NeMo Neural Machine Translation Systems for English-German and English-Russian News and Biomedical Tasks at WMT21
This paper provides an overview of NVIDIA NeMo's neural machine translation systems for the constrained data track of the WMT21 News and Biomedical Shared Translation Tasks.
SPGISpeech: 5,000 hours of transcribed financial audio for fully formatted end-to-end speech recognition
In the English speech-to-text (STT) machine learning task, acoustic models are conventionally trained on uncased Latin characters, and any necessary orthography (such as capitalization, punctuation, and denormalization of non-standard words) is imputed by separate post-processing models.
Ranked #3 on
Speech Recognition
on SPGISpeech
Training Deep Networks with Stochastic Gradient Normalized by Layerwise Adaptive Second Moments
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.
QuartzNet: Deep Automatic Speech Recognition with 1D Time-Channel Separable Convolutions
We propose a new end-to-end neural acoustic model for automatic speech recognition.
Ranked #41 on
Speech Recognition
on LibriSpeech test-clean
Speech Recognition
Audio and Speech Processing
NeMo: a toolkit for building AI applications using Neural Modules
NeMo (Neural Modules) is a Python framework-agnostic toolkit for creating AI applications through re-usability, abstraction, and composition.
Ranked #1 on
Speech Recognition
on Common Voice Spanish
(using extra training data)
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+1
Stochastic Gradient Methods with Layer-wise Adaptive Moments for Training of Deep Networks
We propose NovoGrad, an adaptive stochastic gradient descent method with layer-wise gradient normalization and decoupled weight decay.
Jasper: An End-to-End Convolutional Neural Acoustic Model
In this paper, we report state-of-the-art results on LibriSpeech among end-to-end speech recognition models without any external training data.
Ranked #3 on
Speech Recognition
on Hub5'00 SwitchBoard
OpenSeq2Seq: Extensible Toolkit for Distributed and Mixed Precision Training of Sequence-to-Sequence Models
We present OpenSeq2Seq {--} an open-source toolkit for training sequence-to-sequence models.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Mixed-Precision Training for NLP and Speech Recognition with OpenSeq2Seq
We present OpenSeq2Seq - a TensorFlow-based toolkit for training sequence-to-sequence models that features distributed and mixed-precision training.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+4
Training Deep AutoEncoders for Recommender Systems
Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training.
Mixed Precision Training
Using this approach, we can reduce the memory consumption of deep learning models by nearly 2x.
Training Deep AutoEncoders for Collaborative Filtering
Our model is based on deep autoencoder with 6 layers and is trained end-to-end without any layer-wise pre-training.
Factorization tricks for LSTM networks
We present two simple ways of reducing the number of parameters and accelerating the training of large Long Short-Term Memory (LSTM) networks: the first one is "matrix factorization by design" of LSTM matrix into the product of two smaller matrices, and the second one is partitioning of LSTM matrix, its inputs and states into the independent groups.
Ranked #22 on
Language Modelling
on One Billion Word
