facebookresearch/fairseq

Hybrid CTC/attention decode

Open

#5,015 opened on Mar 8, 2023

View on GitHubContributor guide
 (0 comments) (0 reactions) (0 assignees)Python (6,224 forks)batch import
enhancementhelp wantedneeds triage

Repository metrics

Stars
 (29,107 stars)
PR merge metrics
 (PR metrics pending)

Description

🚀 Feature Request

Hybrid CTC/attention decode is needed in asr task.

Motivation

Hybrid CTC/attention has achieve impressive results is speech recognition. However, i do not find the relevant feature in fairseq, especially when decoding. Paper: Hybrid CTC/attention architecture for end-to-end speech recognition

Pitch

User can easily adopt the hybrid CTC/attention decode.

Contributor guide

Research direction
Study the paper on hybrid CTC/attention ASR decoding, then implement the decoder in fairseq.
Tech stack
pythonpytorch
Domain
machine learningai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Needs investigation
Prerequisites
PythonPyTorchASR
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30