Compare teachers
Assess candidate speech models for naturalness, pronunciation and coverage of the target varieties.
Jarir is a research project exploring a compact text-to-speech model for English, Modern Standard Arabic and Najdi Arabic.
Jarir is being explored as a compact model with randomly initialized student weights. Existing speech models may help produce teaching examples; their weights are not the starting point for the student.
Assess candidate speech models for naturalness, pronunciation and coverage of the target varieties.
Generate and filter text-and-audio examples with clear language, speaker and style labels.
Train a compact student architecture from random initialization and measure what it learns.
Check intelligibility, dialect fit, voice consistency and expressive control before expanding.
These are project goals under investigation, not features of a released model. The pilot will determine which targets fit the available data and compute.
English, Modern Standard Arabic and Najdi Arabic, evaluated separately as well as together.
A compact student is the target range; the final size depends on pilot quality and inference needs.
Explore 6–10 male and female voices, with emotion tags as a controlled research goal.
For research, partnership or project enquiries, contact SJM Labs.