FINDING #7016 · UNIT ID 1207153645
OpenMOSS/MOSS-TTS-Nano
MOSS-TTS-Nano is an open-source multilingual tiny speech generation model from MOSI.AI and the OpenMOSS team. With only 0.1B parameters, it is designed for realtime speech generation, can run directly on CPU without a GPU, and keeps the deployment stack simple enough for local demos, web serving, and lightweight product integration.
SURPRISE SCORE
0.00
Score Breakdown
SCORE = SURPRISE × ENGAGEMENT^0.7 × FRESHNESS × VISIBILITY × CONFIDENCE
SURPRISE = WINDOW STARS / DAYS / (AUDIENCE + FLOOR)
1% OF STARS IN ARCHIVE
Growth Telemetry
VELOCITY /D
8.00
ACCEL
-0.07
RETENTION
55.1%
PEAK 2026-08-22 · FORK-RETENTION 16.7% · 56 STARS / WINDOW
Author Audience
AUDIENCE
8,214
FOLLOWERS
904
OWNER ★
32,032
Engagement Signals
FORKS
544
ISSUE AUTH
0
PR AUTH
0
UNIQUE STARGAZERS 56 / 56 (DIVERSITY 1.00)
Why This Is A Finding
OpenMOSS/MOSS-TTS-Nano собрал 56 звёзд за окно, тогда как у автора всего 904 подписчиков — эффективная аудитория ≈ 8,214. Это даёт surprise-индекс 0.000969 (звёзды относительно охвата автора, а не в абсолюте). Удержание форков 16.7% и 0 внешних контрибьюторов отделяют реальный инструмент от разовой вспышки. Акселерация отрицательная — внимание остывает после пика.
Related Findings
RANKS ABOVE 28% OF 9760 FINDINGS
METRICS IN CONTEXT
MEDIAN ACROSS ALL 9760 FINDINGS · Δ vs MEDIAN · PERCENTILE = SHARE RANKED BELOW
METRICVALUEMEDIANΔ MEDPERCENTILE
SCORE0.000.00-0.00ABOVE 28%
VELOCITY8.003.71+4.29ABOVE 73%
RETENTION55.1%38.0%+17.1 PPABOVE 74%
FORKS54486+458ABOVE 88%
SURPRISE0.000.01-0.01ABOVE 14%