Reson8 open-sources 0.5B speech recognition model
Understand this story
Reson8 has open-sourced Rumble-2-Flash, a 0.5B-parameter speech recognition model, under the Apache 2.0 license, supporting more than 40 languages with automatic language detection. The model weights are published in the Reson8/Rumble-2-Flash repository on Hugging Face Hub, with native support for Transformers and vLLM and no custom code required; Reson8 says it is also available via its API.
AI overview based on source reports · Updated 2 days ago
Coverage timeline
Follow the coverage to explore different perspectives.
- Hugging Face BlogFeaturedRumble-2-Flash: an open 0.5B speech model for 40+ languages
Reson8 has open-sourced Rumble-2-Flash under Apache 2.0, a 0.5B-parameter speech recognition model for 40+ languages with automatic language detection, output controls, and native support in Transformers and vLLM. It reports a 6.96% average error rate on the Open ASR Leaderboard multilingual track and 7.86% WER on AppTek's 302-hour call-centre benchmark, on par with NVIDIA's Nemotron 3.5 Transcribe (30B) at 7.78%. The model was distilled from the larger Rumble-2 using on-policy distillation with GOLD, which merges tokens across differing tokenizers.
Activity for this story
- Current comparable activity
- 3
- Peak comparable activity
- 6Nov 19 00:00
- Change in the past 24 hours
- -49%
Trends compare the same fully observed participants, which may cover fewer participants than current activity. Move the pointer or tap the chart to inspect hourly activity; use the left and right arrow keys with a keyboard.