创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

Reson8发布Rumble-2-Flash开放权重语音模型

AI 总结

Reson8以Apache 2.0许可证发布了拥有开放权重的0.5B参数语音识别模型Rumble-2-Flash。该模型支持40多种语言、自动语言检测和可配置的转录输出,并原生接入Transformers与vLLM。Reson8称,其在满批次下处理一小时音频约需半秒,并在302小时嘈杂呼叫中心基准中与NVIDIA的30B Nemotron 3.5 Transcribe表现相当。

深度见解

这一发布让开发者可在常用推理框架中直接使用免费的多语种ASR模型,但官方公布的速度与准确率数据仍属于厂商声称。

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

原文约 3 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。