Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Reson8 releases open-weight Rumble-2-Flash speech model

AI summary

Reson8 released the 0.5B-parameter Rumble-2-Flash speech recognition model under the Apache 2.0 license with open weights. It supports more than 40 languages, automatic language detection and configurable transcription output, with native integration for Transformers and vLLM. Reson8 claims the model can process an hour of audio in about half a second and performs on par with NVIDIA's 30B Nemotron 3.5 Transcribe on a 302-hour noisy call-centre benchmark.

In-depth insight

The release provides developers with a freely downloadable multilingual ASR model that can run in widely used inference stacks without custom code, while Reson8's speed and accuracy figures remain vendor claims.

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

Transcribe with 🤗 Transformers

uv pip install torch transformers accelerate
from transformers import AutoProcessor, AutoModelForMultimodalLM

model_id = "Reson8/Rumble-2-Flash"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForMultimodalLM.from_pretrained(model_id, device_map="auto")

inputs = processor.apply_transcription_request(
    audio="https://hf.co/datasets/hf-internal-testing/dummy-audio-samples/resolve/main/bcn_weather.mp3",
    language="English",  # omit to detect automatically
).to(model.device, dtype=model.dtype)

output = model.generate(**inputs, max_new_tokens=512)
generated = output[:, inputs["input_ids"].shape[-1]:]
print(processor.decode(generated, return_format="transcription_only")[0])  # return_format="parsed" if detecting language

#Reson8#Rumble-2-Flash#Transformers#vLLM#Qwen3-ASR#NVIDIA Nemotron 3.5 Transcribe#Whisper large-v3#Meta omniASR-LLM

Original · 3 min readRead the original
Group chat

No comments yet. Start the conversation.