# Hugging Face — Rumble-2-Flash: an open 0.5B speech model for 40+ languages

- Company: Hugging Face (huggingface.co)
- Announced: 2026-11-18
- Category: open-weight-release
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/rumble-2-flash
- Record: https://forck.live/items/38003-rumble-2-flash-an-open-0-5b-speech-model-for-40-languages
- Subject: Platform
- Open weights: yes
- Models affected: Rumble-2-Flash, Rumble-2, Qwen3-ASR, Nemotron 3.5 Transcribe, omniASR-LLM 7B, Whisper large-v3
- License: Apache 2.0

Reson8 has open sourced Rumble-2-Flash, a 0.5B-parameter speech recognition model for 40+ languages, under the Apache 2.0 license. The model is distilled from Rumble-2, the company's larger production model, using on-policy distillation, where the student transcribes audio itself and the teacher grades each token rather than supplying transcripts. Because the two models use different tokenizers, the team used GOLD to merge tokens where the tokenizers split text differently so both are compared over the same text. On the Open ASR Leaderboard multilingual track, Rumble-2-Flash averages a 6.96% error rate across nine languages, which the company says beats Meta's omniASR-LLM 7B, a model 15x larger, and Whisper large-v3. On AppTek's 302-hour call-centre benchmark with 14 English accents, it reaches 7.86% WER, on par with NVIDIA's Nemotron 3.5 Transcribe (30B) at 7.78%. The weights are on the Hub at Reson8/Rumble-2-Flash and it is also available through the company's API.

## Evidence

Verbatim from https://huggingface.co/blog/rumble-2-flash:

> Today we're open sourcing Rumble-2-Flash under the Apache 2.0 license. It's a 0.5B-parameter speech recognition model for 40+ languages that competes with models 3-60x its size.
> 
> Runs anywhere : native support in 🤗 Transformers and vLLM, no custom code
> 
> 40+ languages : automatic language detection
> 
> Output control : numbers as digits or words, fillers, verbatim repeats, forced language
> 
> Extremely fast : an hour of audio in about half a second, with over 7,000 RTFx on full batches
> 
> Holds up on real phone calls : on par with NVIDIA's Nemotron 3.5 Transcribe (30B) on a 302-hour call-centre benchmark
> 
> Quickstart
> 
> uv pip install torch transformers accelerate

---

Record: https://forck.live/items/38003-rumble-2-flash-an-open-0-5b-speech-model-for-40-languages
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md
