Alert button
Picture for Jacob Kahn

Jacob Kahn

Alert button

TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch

Oct 27, 2023
Jeff Hwang, Moto Hira, Caroline Chen, Xiaohui Zhang, Zhaoheng Ni, Guangzhi Sun, Pingchuan Ma, Ruizhe Huang, Vineel Pratap, Yuekai Zhang, Anurag Kumar, Chin-Yun Yu, Chuang Zhu, Chunxi Liu, Jacob Kahn, Mirco Ravanelli, Peng Sun, Shinji Watanabe, Yangyang Shi, Yumeng Tao, Robin Scheibler, Samuele Cornell, Sean Kim, Stavros Petridis

Figure 1 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 2 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 3 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Figure 4 for TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
Viaarxiv icon

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Oct 08, 2023
Xi Victoria Lin, Xilun Chen, Mingda Chen, Weijia Shi, Maria Lomeli, Rich James, Pedro Rodriguez, Jacob Kahn, Gergely Szilvasy, Mike Lewis, Luke Zettlemoyer, Scott Yih

Figure 1 for RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Figure 2 for RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Figure 3 for RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Figure 4 for RA-DIT: Retrieval-Augmented Dual Instruction Tuning
Viaarxiv icon

The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment

Feb 13, 2023
Jared Fernandez, Jacob Kahn, Clara Na, Yonatan Bisk, Emma Strubell

Figure 1 for The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment
Figure 2 for The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment
Figure 3 for The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment
Figure 4 for The Framework Tax: Disparities Between Inference Efficiency in Research and Deployment
Viaarxiv icon

OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks

Nov 02, 2022
Benoit Steiner, Mostafa Elhoushi, Jacob Kahn, James Hegarty

Figure 1 for OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
Figure 2 for OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
Figure 3 for OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
Figure 4 for OLLA: Optimizing the Lifetime and Location of Arrays to Reduce the Memory Usage of Neural Networks
Viaarxiv icon

Reasoning over Public and Private Data in Retrieval-Based Systems

Mar 14, 2022
Simran Arora, Patrick Lewis, Angela Fan, Jacob Kahn, Christopher Ré

Figure 1 for Reasoning over Public and Private Data in Retrieval-Based Systems
Figure 2 for Reasoning over Public and Private Data in Retrieval-Based Systems
Figure 3 for Reasoning over Public and Private Data in Retrieval-Based Systems
Figure 4 for Reasoning over Public and Private Data in Retrieval-Based Systems
Viaarxiv icon

Flashlight: Enabling Innovation in Tools for Machine Learning

Jan 29, 2022
Jacob Kahn, Vineel Pratap, Tatiana Likhomanenko, Qiantong Xu, Awni Hannun, Jeff Cai, Paden Tomasello, Ann Lee, Edouard Grave, Gilad Avidov, Benoit Steiner, Vitaliy Liptchinsky, Gabriel Synnaeve, Ronan Collobert

Figure 1 for Flashlight: Enabling Innovation in Tools for Machine Learning
Figure 2 for Flashlight: Enabling Innovation in Tools for Machine Learning
Figure 3 for Flashlight: Enabling Innovation in Tools for Machine Learning
Figure 4 for Flashlight: Enabling Innovation in Tools for Machine Learning
Viaarxiv icon

Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training

Apr 02, 2021
Wei-Ning Hsu, Anuroop Sriram, Alexei Baevski, Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Jacob Kahn, Ann Lee, Ronan Collobert, Gabriel Synnaeve, Michael Auli

Figure 1 for Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Figure 2 for Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Figure 3 for Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Figure 4 for Robust wav2vec 2.0: Analyzing Domain Shift in Self-Supervised Pre-Training
Viaarxiv icon

Rethinking Evaluation in ASR: Are Our Models Robust Enough?

Oct 22, 2020
Tatiana Likhomanenko, Qiantong Xu, Vineel Pratap, Paden Tomasello, Jacob Kahn, Gilad Avidov, Ronan Collobert, Gabriel Synnaeve

Figure 1 for Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Figure 2 for Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Figure 3 for Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Figure 4 for Rethinking Evaluation in ASR: Are Our Models Robust Enough?
Viaarxiv icon

slimIPL: Language-Model-Free Iterative Pseudo-Labeling

Oct 22, 2020
Tatiana Likhomanenko, Qiantong Xu, Jacob Kahn, Gabriel Synnaeve, Ronan Collobert

Figure 1 for slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Figure 2 for slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Figure 3 for slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Figure 4 for slimIPL: Language-Model-Free Iterative Pseudo-Labeling
Viaarxiv icon

Differentiable Weighted Finite-State Transducers

Oct 02, 2020
Awni Hannun, Vineel Pratap, Jacob Kahn, Wei-Ning Hsu

Figure 1 for Differentiable Weighted Finite-State Transducers
Figure 2 for Differentiable Weighted Finite-State Transducers
Figure 3 for Differentiable Weighted Finite-State Transducers
Figure 4 for Differentiable Weighted Finite-State Transducers
Viaarxiv icon