epitran
A tool for transcribing orthographic text as IPA (International Phonetic Alphabet) (by dmort27)
Phonetisaurus
Phonetisaurus G2P (by AdolfVonKleist)
epitran | Phonetisaurus | |
---|---|---|
2 | 1 | |
584 | 433 | |
- | - | |
7.5 | 0.0 | |
about 1 month ago | 2 months ago | |
Python | Shell | |
MIT License | BSD 3-clause "New" or "Revised" License |
The number of mentions indicates the total number of mentions that we've tracked plus the number of user suggested alternatives.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
epitran
Posts with mentions or reviews of epitran.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-04-20.
-
Is there a software/site that would transcribe English texts into IPA (relatively long texts)?
For one research project we used epitran: https://github.com/dmort27/epitran
-
The difficulties of transcribing tone. Or, what's the goal of transcribing IPA with Machine Learning?
It would seem ML is well placed to handle the world of phonemes (fundamental categories) and phones (permutations on those categories). Indeed, Facebook has a mature project and set of pre-trained ML models for something similar, if not identical: wav2vec (v2.0). If it's not identical then I think it'd be trivial to achieve. Wav2vec is trained to map the spoken word of a language to that language's particular writing system, see here for a specific example. However, we already have plenty of software that can convert writing systems to IPA. Whilst all that does connect a lot of dots, it's not exactly what I think the goal should be.
Phonetisaurus
Posts with mentions or reviews of Phonetisaurus.
We have used some of these posts to build our list of alternatives
and similar projects. The last one was on 2023-04-20.
-
Is there a software/site that would transcribe English texts into IPA (relatively long texts)?
Some of the more popular tools for this include Sequitur and Phonetisaurus. It would also probably not be too hard to train something in PyTorch/Keras.
What are some alternatives?
When comparing epitran and Phonetisaurus you can also consider the following projects:
this-word-does-not-exist - This Word Does Not Exist
zeroth - Kaldi-based Korean ASR (한국어 음성인식) open-source project