LLM Digest
Subscribe

AI Storyline

3 items · 3 sources · 3 days

View as JSON

Operational story trace

Speech Recognition

Latest change

Earlybird, a 29M-parameter predictive streaming recognizer, targets the 90-400 ms that streaming ASR typically waits after a speaker finishes a word before outputting it, a delay it frames as a voice-agent cost.

Earlier contextThe story so far

This is a topical cluster of three independent arXiv papers on speech recognition, not one unfolding event. A late-October paper ran Kroko, a 65.7M-parameter streaming Zipformer2 transducer, at 2 and 4 bits on an ESP32-P4 microcontroller with no neural accelerator, and a second argued that ASR benchmarks still assume a single ground-truth transcript per utterance.

editor-curated · source-linked

Arc

Oct 28Nov 10 · now
FOOTPRINT · Oct 28
A 65.7M-parameter streaming transducer runs on an ESP32-P4 in 2 and 4 bits
1 source · show source ▾
EVALUATION · Oct 30
A benchmark proposal for grounded generative speech recognition
1 source · show source ▾
LATENCY · Nov 10
Earlybird predicts words early to cut streaming lag in 29M parameters
1 source · show source ▾

What to watch — open questions

  • What accuracy does the 2-bit and 4-bit Kroko encoder lose against the full-precision model, and does it run in real time on the ESP32-P4?
  • How much of the 90-400 ms output delay does Earlybird remove, and at what word-error cost when a prediction is wrong?
  • Do existing speech language models rank differently under a grounded generative benchmark than under single-reference WER?
  • Does any of the three papers ship code or weights that others can reproduce?
How this thread was built
editor wrote the arc · 3 beats

Storylines are threaded mechanically from the feed: stories that share a distinctive anchor across multiple days and sources. Each item links to its original source. The evidence trace, current state, and open questions are written by the editor routine and refreshed whenever a new beat lands.