Rumble-2-Flash: an open 0.5B speech model for 40+ languages
Back to Articles a]:hidden"> Rumble-2-Flash: an open 0. 5B speech model for 40+ languages Published November 18, 2026 Update on GitHub Upvote 8 +2 Reson8…
Summary
Back to Articles a]:hidden"> Rumble-2-Flash: an open 0. 5B speech model for 40+ languages Published November 18, 2026 Update on GitHub Upvote 8 +2 Reson8 reson8-thomas Follow Reson8 Mark 't Hart MarktHart Follow Reson8 Eustache Le Bihan eustlb Follow Eric Bezzam bezzam Follow:last-child]:mb-0"> Today we're open sourcing Rumble-2-Flash under the Apache 2. 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.
Positives
- Back to Articles a]:hidden"> Rumble-2-Flash: an open 0.
- 5B speech model for 40+ languages Published November 18, 2026 Update on GitHub Upvote 8 +2 Reson8 reson8-thomas Follow Reson8 Mark 't Hart MarktHart Follow Reson8 Eustache Le Bihan eustlb Follow Eric Bezzam bezzam Follow:last-child]:mb-0"> Today we're open sourcing Rumble-2-Flash under the Apache 2.
Risks & concerns
- The article may not provide enough evidence to validate every implication.
- Execution, cost, adoption, regulation, or security could change the outcome.