Tech Meridian ← ENTITY INDEX
PROMY MERIDIAN RU

MODEL · ENTITY #9485

Whisper

Related event timeline, sources and context from the news index.

EVENT TIMELINE

2

MODELS · 2 SOURCES · Mistral AI · The Decoder

Mistral releases Voxtral 3 voice-agent SDK and multilingual speech models

Mistral announced Voxtral 3, a family of speech-to-text and text-to-speech models plus a real-time voice agent SDK for multi-step conversations in 50+ languages; components include Voxtral Small Transcribe 3, Voxtral Mini TTS 3, and Pro Voice. The offering is available via Mistral’s EU-hosted API or for self-deployment, and Mistral says the Transcribe models achieve state-of-the-art diarization and multilingual transcription, claiming outperformance of Whisper, Scribe v2 and Gemini 3.5 Transcribe on selected benchmarks.

8.0

RESEARCH · 1 SOURCE · arXiv cs.AI

Pretrained ASR pseudo-labeling for noisy police audio uses LLM judging (arXiv:2609.30469v1)

This arXiv paper evaluates pseudo-labeling to adapt foundation ASR models (Whisper and Qwen3-ASR) to very noisy Broadcast Police Communication (BPC) corpora from Baltimore and Chicago. The authors find internal confidence metrics (log-probabilities, STAR scores) poorly separate good from bad pseudo-labels, propose an external LLM-as-a-judge filtering paradigm that discards contextually implausible transcripts and reduces WER of pseudo-labeled training sets, and introduce a cross-model pseudo-labeling approach where one model is fine-tuned on pseudo-labels from another.

6.0