mozilla/DeepSpeech

Benchmark the CTC against a RNN-Transducer model

Open

#753 opened on Aug 6, 2017

View on GitHubContributor guide
 (2 comments) (1 reaction) (0 assignees)C++ (4,093 forks)batch import
Priority: P3enhancementhelp wantedserver time

Repository metrics

Stars
 (26,755 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

This issue does not include a description.

Contributor guide

Research direction
Set up DeepSpeech development environment. Understand the CTC and RNN Transducer models. Create benchmark scripts to measure training time, inference speed, accuracy on common datasets. Compare results and document findings.
Tech stack
pythontensorflow
Domain
machine learningaiperformance
Issue type
Research
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
4
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
3-5 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
Deep Learning conceptsPythonTensorFlowSpeech recognition basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
30