Open source #Open models Nov 19, 2026 · Originally published Nov 18

Rumble-2-Flash is open-sourced under Apache 2.0: a 0.5B-parameter speech recognition model for 40+ languages, averaging 6.96% error on the multilingual track

A multilingual speech recognition model small enough for modest hardware, with native Transformers and vLLM support. For teams that need self-hosted transcription and care about Chinese.

Image: Hugging Face Blog
Primary source Hugging Face Blog · huggingface.co Read the original ↗

// Key points

  • 0.5B parameters with automatic detection across 40+ languages; it uses the Qwen3-ASR architecture, with native Transformers and vLLM support and no custom code.
  • On the Open ASR Leaderboard multilingual track (nine languages including Chinese, German, French and Hindi) it averages a 6.96% error rate, better than Meta's omniASR-LLM 7B, 15x larger, and Whisper large-v3; English WER averages 6.6%.
  • Throughput exceeds 7,000 RTFx on full batches, about half a second per hour of audio; on a 302-hour call-centre benchmark it is on par with NVIDIA's Nemotron 3.5 Transcribe (30B).
  • It was distilled from the larger Rumble-2 with on-policy distillation, using GOLD to handle teacher and student having different tokenizers.

Builder's takeAI Interview transcribes candidate answers before analyzing them, and a 0.5B Apache 2.0 model that runs on vLLM could replace per-minute cloud transcription. I would test character error rate on real Chinese interview recordings, focusing on accents and mixed Chinese-English. Its phone-call result is an English benchmark, so verify Chinese yourself.

// Background · from #Open models

Full timeline →
  1. Nov 19 Cloudflare opens the weights of Clairic and Clairic-flash: 27B and 9B extraction models that read PDFs and bill only for input tokens
  2. Nov 19 Hugging Face shows Transformers streaming MoE experts from SSD: a 180B-parameter model runs at about 14 tok/s on a 32 GB MacBook
  3. Nov 19 AWS Lambda Managed Instances adds GPUs: run inference functions on EC2 G-series instances, with vLLM, SGLang and PyTorch base images

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →