Trendoday

Marimba: A System One Model for Speech

Speech applications require decisions about term presence, turn completion, and language within an audio window. We present Marimba, an interface for typed speech decisions built on frozen Qwen3-ASR 0

  • Upvotes3
–Rank now
#21Peak rank
3Days on list
94Score · 7d
Nov 17, 2026First seen
Rank · 7 days

About this paper

Marimba uses frozen Qwen3-ASR features and lightweight readouts to make lexical, turn-end, language, speaker-change, and personal-information decisions from speech, achieving strong detection and calibration on conversational and read-speech benchmarks.

Speech applications require decisions about term presence, turn completion, and language within an audio window. We present Marimba, an interface for typed speech decisions built on frozen Qwen3-ASR 0.6B features. Lexical questions use zero-shot scoring of ASR transcripts; non-lexical questions use a question-conditioned head and a separate layer-18 turn-end readout. Language identification uses the ASR model's own language scores. On private conversational test sets, decoder AUROC is 0.80-0.92; on public read speech it is 0.92-0.97. Speech Commands four-way accuracy is 0.93; binary lexical ECE is at most 0.08. Personal-information detection, which passes the greedy transcript to a…

Marimbafrozen Qwen3-ASR 0.6B featureszero-shot scoringASR transcriptsquestion-conditioned headlayer-18 turn-end readoutlanguage identificationdecoder AUROCSpeech CommandsECE
Upvotes
3
Authors
1
Published
Nov 13, 2026

Summary and abstract excerpt via Hugging Face Papers ↗ · arXiv.

Trending history

Marimba: A System One Model for Speech was first seen on Hugging Face · Daily papers on Nov 17, 2026. Since then it has appeared in 15 checks on 3 different days. Its best position was #21 of 30, reached on Nov 18, 15:28 UTC. It dropped off the list after Nov 19, 01:28 UTC.

Rank history

Position on Hugging Face · Daily papers at every check (lower is better).

#1#11#20#30 21:2804:2811:2818:2801:28 Nov 17, 21:28 UTC · #29Nov 17, 23:28 UTC · #25Nov 18, 01:28 UTC · #24Nov 18, 03:28 UTC · #30Nov 18, 05:28 UTC · #22Nov 18, 07:28 UTC · #22Nov 18, 09:28 UTC · #30Nov 18, 11:28 UTC · #30Nov 18, 13:28 UTC · #23Nov 18, 15:28 UTC · #21Nov 18, 17:28 UTC · #21Nov 18, 19:28 UTC · #22Nov 18, 21:28 UTC · #22Nov 18, 23:28 UTC · #22Nov 19, 01:28 UTC · #22

Last 14 days

Best rank per day (UTC).

Nov 9today

Metric history

Platform metric as reported by Hugging Face.

0257 21:2804:2811:2818:2801:28 Nov 17, 21:28 UTC · 3Nov 17, 23:28 UTC · 4Nov 18, 01:28 UTC · 4Nov 18, 03:28 UTC · 4Nov 18, 05:28 UTC · 6Nov 18, 07:28 UTC · 7Nov 18, 09:28 UTC · 7Nov 18, 11:28 UTC · 7Nov 18, 13:28 UTC · 6Nov 18, 15:28 UTC · 6Nov 18, 17:28 UTC · 6Nov 18, 19:28 UTC · 6Nov 18, 21:28 UTC · 6Nov 18, 23:28 UTC · 6Nov 19, 01:28 UTC · 6

Questions

Is Marimba: A System One Model for Speech trending on HF Daily Papers right now?

Not at the moment. It was last on the list on Nov 19, 01:28 UTC, after 3 days of trending.

What is the highest rank Marimba: A System One Model for Speech reached?

#21 on Hugging Face · Daily papers, on Nov 18, 15:28 UTC. Trendoday checks this list every 120 minutes.

How long has Marimba: A System One Model for Speech been trending?

It was first seen on Nov 17, 2026 and has been on the list on 3 days (15 checks) since.