Reka Speech High Throughput Speech Transcription And Translation Model With Timestamps
Source
Reka AI editorial sitemap
Author
Reka AI editorial sitemap
Date
Terms in this piece · Glossary
attention — The mechanism that lets a model weigh which earlier words matter for the word it's currently processing — the core operation of a transformer.
alignment — The work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.
Why it matters
An 850M speech model that produces timestamped transcription and translation 8-35x faster than WhisperX and faster-whisper on a single H100, using a QK-offload-and-recompute alignmentThe work of making AI systems actually pursue what their builders and users intend, rather than something subtly or dangerously different.Full definition → pass instead of a separate forced-alignment model.
