Jacob Kahn
Jacob Kahn
Facebook AI Research
Verified email at - Homepage
Cited by
Cited by
Libri-Light: A Benchmark for ASR with Limited or No Supervision
J Kahn, M Rivière, W Zheng, E Kharitonov, Q Xu, PE Mazaré, J Karadayi, ...
ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and …, 2020
End-to-End ASR: from Supervised to Semi-Supervised Learning with Modern Architectures
G Synnaeve, Q Xu, J Kahn, E Grave, T Likhomanenko, V Pratap, A Sriram, ...
arXiv preprint arXiv:1911.08460, 2019
Self-Training for End-to-End Speech Recognition
J Kahn, A Lee, A Hannun
arXiv preprint arXiv:1909.09116, 2019
Robust wav2vec 2.0: Analyzing domain shift in self-supervised pre-training
WN Hsu, A Sriram, A Baevski, T Likhomanenko, Q Xu, V Pratap, J Kahn, ...
arXiv preprint arXiv:2104.01027, 2021
Wav2Letter++: A Fast Open-source Speech Recognition System
V Pratap, A Hannun, Q Xu, J Cai, J Kahn, G Synnaeve, V Liptchinsky, ...
ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and …, 2019
Iterative pseudo-labeling for speech recognition
Q Xu, T Likhomanenko, J Kahn, A Hannun, G Synnaeve, R Collobert
arXiv preprint arXiv:2005.09267, 2020
Rethinking evaluation in asr: Are our models robust enough?
T Likhomanenko, Q Xu, V Pratap, P Tomasello, J Kahn, G Avidov, ...
arXiv preprint arXiv:2010.11745, 2020
slimipl: Language-model-free iterative pseudo-labeling
T Likhomanenko, Q Xu, J Kahn, G Synnaeve, R Collobert
arXiv preprint arXiv:2010.11524, 2020
Ra-dit: Retrieval-augmented dual instruction tuning
XV Lin, X Chen, M Chen, W Shi, M Lomeli, R James, P Rodriguez, J Kahn, ...
arXiv preprint arXiv:2310.01352, 2023
Scaling Up Online Speech Recognition Using ConvNets
V Pratap, Q Xu, J Kahn, G Avidov, T Likhomanenko, A Hannun, ...
Differentiable weighted finite-state transducers
A Hannun, V Pratap, J Kahn, WN Hsu
arXiv preprint arXiv:2010.01003, 2020
Flashlight: Enabling innovation in tools for machine learning
JD Kahn, V Pratap, T Likhomanenko, Q Xu, A Hannun, J Cai, P Tomasello, ...
International Conference on Machine Learning, 10557-10574, 2022
Reasoning over public and private data in retrieval-based systems
S Arora, P Lewis, A Fan, J Kahn, C Ré
Transactions of the Association for Computational Linguistics 11, 902-921, 2023
Chameleon: Mixed-modal early-fusion foundation models
C Team
arXiv preprint arXiv:2405.09818, 2024
OLLA: Decreasing the Memory Usage of Neural Networks by Optimizing the Lifetime and Location of Arrays.
B Steiner, M Elhoushi, J Kahn, J Hegarty
CoRR, 2022
TorchAudio 2.1: Advancing speech recognition, self-supervised learning, and audio processing components for PyTorch
J Hwang, M Hira, C Chen, X Zhang, Z Ni, G Sun, P Ma, R Huang, V Pratap, ...
2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), 1-9, 2023
The Framework Tax: Disparities Between Inference Efficiency in NLP Research and Deployment
J Fernandez, J Kahn, C Na, Y Bisk, E Strubell
arXiv preprint arXiv:2302.06117, 2023
Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM
S Sukhbaatar, O Golovneva, V Sharma, H Xu, XV Lin, B Rozière, J Kahn, ...
arXiv preprint arXiv:2403.07816, 2024
The system can't perform the operation now. Try again later.
Articles 1–18