Picture for Ryan Prenger

Ryan Prenger

Upcycling Large Language Models into Mixture of Experts

Add code
Oct 10, 2024
Viaarxiv icon

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

Add code
Jun 27, 2023
Figure 1 for LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Figure 2 for LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Figure 3 for LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Figure 4 for LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Viaarxiv icon

Context Generation Improves Open Domain Question Answering

Add code
Oct 12, 2022
Figure 1 for Context Generation Improves Open Domain Question Answering
Figure 2 for Context Generation Improves Open Domain Question Answering
Figure 3 for Context Generation Improves Open Domain Question Answering
Figure 4 for Context Generation Improves Open Domain Question Answering
Viaarxiv icon

Multi-Stage Prompting for Knowledgeable Dialogue Generation

Add code
Mar 16, 2022
Figure 1 for Multi-Stage Prompting for Knowledgeable Dialogue Generation
Figure 2 for Multi-Stage Prompting for Knowledgeable Dialogue Generation
Figure 3 for Multi-Stage Prompting for Knowledgeable Dialogue Generation
Figure 4 for Multi-Stage Prompting for Knowledgeable Dialogue Generation
Viaarxiv icon

Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis

Add code
May 13, 2020
Figure 1 for Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Figure 2 for Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Figure 3 for Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Figure 4 for Flowtron: an Autoregressive Flow-based Generative Network for Text-to-Speech Synthesis
Viaarxiv icon

Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens

Add code
Oct 26, 2019
Figure 1 for Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens
Figure 2 for Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens
Figure 3 for Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens
Viaarxiv icon

WaveGlow: A Flow-based Generative Network for Speech Synthesis

Add code
Oct 31, 2018
Figure 1 for WaveGlow: A Flow-based Generative Network for Speech Synthesis
Figure 2 for WaveGlow: A Flow-based Generative Network for Speech Synthesis
Viaarxiv icon

Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting

Add code
Jul 04, 2017
Figure 1 for Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Figure 2 for Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Figure 3 for Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Figure 4 for Convolutional Recurrent Neural Networks for Small-Footprint Keyword Spotting
Viaarxiv icon

Deep Speech 2: End-to-End Speech Recognition in English and Mandarin

Add code
Dec 08, 2015
Figure 1 for Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Figure 2 for Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Figure 3 for Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Figure 4 for Deep Speech 2: End-to-End Speech Recognition in English and Mandarin
Viaarxiv icon

Deep Speech: Scaling up end-to-end speech recognition

Add code
Dec 19, 2014
Figure 1 for Deep Speech: Scaling up end-to-end speech recognition
Figure 2 for Deep Speech: Scaling up end-to-end speech recognition
Figure 3 for Deep Speech: Scaling up end-to-end speech recognition
Figure 4 for Deep Speech: Scaling up end-to-end speech recognition
Viaarxiv icon