Three desks. One review step.

Phoenix Rising Group turns spoken statements into draft forms for police desks, job centres, and weigh stations. An officer reviews every line before anything is saved. SASR Eval stays a research note.

You talk. It writes the file.

Spoken Somali, Afar, Arabic, and French become a filled-in form. Emploi Assist, VoiceDoc, and Transport are the desks.

A person checks it

Record, draft, review, export. Nothing is saved until a person signs off.

Four languages

Somali, Afar, Arabic, and French. Built for public service desks in Djibouti.

SASR Eval: a research yardstick, not a live product.

Public-data validation on 50 clips (~550 seconds) stays up as a long-game Somali ASR yardstick. The ASR lab track is frozen. Scores are not a homepage product claim. Full SASR Eval results.

Component Specification Status
Base model Whisper small (244M parameters), fine-tuned Deployed
Training ~1 hour on a single T4 GPU, 500 training steps Complete
Public-data evaluation SASR Eval: 50 clips, ~550 seconds, ground-truth WER/CER Complete (June 2026)
Broadcast-domain evaluation In-domain broadcast recordings from regional archives Frozen / unpublished
Stage Public-data yardstick. Live work is the three desks. Research (frozen track)

Built for Horn of Africa broadcast and archives.

We are building infrastructure to process decades of broadcast data from the Horn of Africa including news, interviews, and cultural programming in Somali and regional languages. Archive work stays with Horn Transcribe. The desks are for forms a person checks.

Regional broadcast coverage

Designed for continuous ingestion of Horn of Africa media from Djibouti, Somaliland, and adjacent territories where language technology has limited reach.

Archive processing pipeline

Infrastructure to digitize, transcribe, and index historical broadcast recordings. Enables retrospective analysis alongside ongoing archival work.

Partner details on request

Detailed data access terms, archive specifications, and collection methodology are shared with qualified research and institutional partners under NDA.

Measured gap vs. commercial ASR

Commercial systems underperform on Somali (WER 0.59–0.87 on the public evaluation set). Fine-tuned Whisper-small at WER 0.368 is the current public-data result.

Public disclosure policy. We do not publicly claim exclusive data access until agreements are fully executed. General capabilities are described here; specific archive details are shared with qualified partners only.

Led by Radwan Jama.

Phoenix Rising Group is led by Radwan Jama, a software engineer with experience in applied machine learning and large-scale systems (Palo Alto Networks, Google Fellowship, Fidelity). He is building Phoenix Rising Group independently, focused on speech technology for Somali and other Horn of Africa languages.

The project combines:

  • Desk tools: Emploi Assist, VoiceDoc, and Transport
  • Record, draft, review, export. A person signs off before anything is saved.
  • SASR Eval, a public research note for Somali speech recognition

Radwan studied Computer Science at Colgate University and has previously worked on ML-powered static analysis, large-scale systems, and AI security tooling. He built and validated SASR Eval end-to-end: dataset construction, model training, and benchmark scoring.

Research, archival, and institutional partners.

Research and cultural institutions

Universities, archives, and language programs focused on Horn of Africa languages and low-resource speech technology.

Documentation and archival organizations

Groups digitizing broadcast, oral history, and cultural collections that need reliable Somali and regional-language transcription.

Institutional partners

Public-sector and regional institutions exploring speech-enabled documentation workflows in Djibouti and the wider Horn of Africa.

See the desks.

Emploi Assist, VoiceDoc, and Transport are the desks. SASR Eval remains a research note.