Aeneas
Dev tools
audio text alignment
SHOW HN2017
188points
35comments
#184of 2,242 in 2017
Top 9%of 2017 by points
How HN took it
LovedMost comments that take a side are positive
7 positive, 9 neutral or asking, 0 mixed, 1 critical, out of 17 comments about the project. Thread score +0.34.
Idea: 5 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Useful for captioning and transcript alignment
From 2 comments
This is super cool. I'm trying to think of common practical applications for this - would one use this to sync a script with a performance? Could this remove a lot of the work…
psobot on HNThanks for creating this. I can imagine a not-so-distant future where thousands of random video-watchers could annotate tiny parts of videos via some free-form box, and aeneas…
TuringNYC on HN
Easy to install and run compared to other aligners
From 1 comment
I would like to note once again that aeneas is not based on automatic speech recognition techniques, but on MFCC + DTW, which is an even older approach, with pro's and con's.…
alpe on HN
Objections
Struggles with non-speech audio such as singing
From 2 comments
Thank you. Indeed several users of aeneas adopted it for producing SRT/TTML files, i.e. captions, for videos, both online and offline --- and many of them start with an existing…
alpe on HNI would like to note once again that aeneas is not based on automatic speech recognition techniques, but on MFCC + DTW, which is an even older approach, with pro's and con's.…
alpe on HN
Less accurate than ASR aligners at word level
From 2 comments
I would like to note once again that aeneas is not based on automatic speech recognition techniques, but on MFCC + DTW, which is an even older approach, with pro's and con's.…
alpe on HNYes, there are several other open source aligners out there, mostly from academic research or derived from academic projects. In my personal GitHub page I have a repo with an…
alpe on HN
Requests
Support for user-defined non-speech intervals
From 1 comment
> there are limitations on the amount of "non speech" that aeneas can tolerate couldn't you have as part of the input also a very simple map where users could define times that…
tetraodonpuffer on HN
Conda package
From 1 comment
This is really cool! Would you like me to make a conda package for this? I can do so for Linux and OSX so that someone who uses python for data science can do `conda install…
afarrell on HN
Live microphone alignment
From 1 comment
Do you know of any existing forced alignment tools that work well with live audio (microphone) input? I would like to create a live stream in which the words of a known text are…
hftf on HN
Questions
What is the alignment accuracy?
From 1 comment
What's the accuracy level of alignment?
braindead_in on HN
Does it work with gaps in the transcript?
From 1 comment
Thanks for the explanation. Will it work if there are gaps in the transcript? Eg, the clean verbatim transcript where the ah's and uhm's are left out.
braindead_in on HN
Alternatives named
Gentle
From 1 comment
This code is also useful <https://github.com/lowerquality/gentle>
oulipo on HN
Kaldi
From 1 comment
I agree on most of your observations. However, please note that other tools are better suited than aeneas if one wants to align at phoneme level: gentle, Kaldi, SPPAS, etc.…
alpe on HN
CMU Sphinx
From 1 comment
For sure aeneas is not suitable, since it requires all the text and all the audio in advance. But ASR-based tools in theory would allow such an operation mode, but I have not…
alpe on HN