FUTO releases ASR4ALL speech recognition models for CPU and mobile devices
FUTO says it has released three streaming speech recognition models with 28 million, 56 million and 97 million parameters, designed for local CPU use.
Event / data period: 2026-10-13
Published: · Updated:
FUTO announced ASR4ALL speech recognition models on October 13. The company said the small, medium and large versions contain 28 million, 56 million and 97 million parameters, respectively, and support streaming output while audio is being received.
FUTO says it designed the models to use ordinary CPU instructions and run locally. It also described a 5.3-million-parameter punctuation, capitalization and error-correction component called PCEC, plus a voice-activity detector that it says adds 2.5 thousand parameters. Training and performance statements are the company’s own reports, not independent benchmark findings.
Data
ASR4ALL model announcement
FUTO introduced three streaming ASR models for local CPU use; parameter counts are rounded figures reported by the company.
- · Occurred
FUTO announces ASR4ALL speech recognition models
FUTO introduced three streaming ASR models for local CPU use; parameter counts are rounded figures reported by the company.
Methodology
Based on FUTO’s October 13 announcement. Parameter counts are rounded as reported by the source; no independent performance result is inferred.
Updated:
Subjects and places
Subject proposals
- Science and technologySuggested
- Preserved editorial category/topic; broad candidate onlyfuto.org ↗
Geographic references
Only source-provided geographic references are shown. Opening an external map is optional. Optional story maps use OpenStreetMap. Opening a map sends your IP address and this site’s address to the map provider; location data remains readable as text without loading the map.
- United States · Place role: Coverage · Place type: Country or area · Location precision: RegionalEvidence
- Explicit preserved editorial country/region; no city or national centroid inferredfuto.org ↗