Modeltiming

The nyra forced aligner

Phoneme
granular alignment, down to the individual sound, not just words
Robust
built for spontaneous, disfluent, imperfect real-world speech
Explicit
fillers, laughs, breaths and vocal sounds modeled as first-class events

The nyra forced aligner is our upcoming phoneme-level aligner for real-world speech. It is built to answer, precisely, which sound happens when, and for how long, even when the speech is anything but clean.

Forced aligners take audio and a transcript and return where in time each unit of speech lives. Most of them fall short in one of three ways: they are not granular enough, stopping at word boundaries when deeper analysis needs phonemes; they are not robust enough, tuned to read-aloud studio recordings and brittle on spontaneous, accented, noisy speech; or they have no explicit model of fillers, laughs, breaths, and other vocal sounds, so when those occur, and in real speech they always do, the aligner smears them onto the neighboring words and the alignment around them quietly corrupts.

The nyra forced aligner tackles all three at once: phoneme-level granularity, robustness to speech as it is actually spoken, and first-class modeling of the events other aligners pretend do not exist.

It is “the when” of the measuring line of our research program: knowing which sound occurs, exactly when, and for how long is the substrate that lets us design losses and supervision that attach to the exact frames where a phenomenon lives.

Coming soon

The model and the full write-up are coming soon!

The deep dive into how the aligner is built, how it handles disfluent and imperfect speech, and how it performs against existing aligners is on its way, together with the model itself.

In the meantime, read how CrisperWhisper 2.0 already extracts word-level timings from its decoder in Turning emergent cross-attention into a precise aligner.