Updates · Podcast
Hebrish Updates
Voice notes from Daniel Rosehill on the project: what is being trained, what is changing in the apps, and why. Each one has a waveform player, chapters and a written version.
Subscribe to Hebrish Updates, the podcast of these voice notes. Each episode comes with chapters and a written version.
Any other podcast app: add https://hebrish.app/updates/feed.xml.
-
Why I built this, 25 hours of recordings and the two models I'm keeping
A voice note from home on a sick day: why the site now says why Hebrish exists, what recording 25 hours of sentences is like, and which models I'm committed to retraining.
-
Recording on Jaffa Street: accuracy, cleanup models and more voices
Recorded on Jaffa Street in Jerusalem: where accuracy caps out, what belongs in the speech model versus post-processing, number and date formatting, disfluencies, learning from my own mistranscriptions, and synthetic voices through IPA.
-
Project update and next sprint
What Hebrish is, why it exists, how the models are trained, the model lines, how the training data is recorded, and the plans for the desktop and Android apps.