AIsaAIsaStudio 中文 Open AIsa Studio

Reson8 releases Rumble-2-Flash, a 0.5B speech recognition model with 45-language support

Original title: Reson8/Rumble-2-Flash (automatic-speech-recognition)

Reson8's Rumble-2-Flash is a 0.5B-parameter speech recognition model with native Transformers and vLLM support, Apache 2.0 licensed, based on Qwen3-ASR-0.6B and covering 45 languages. On the Open ASR Leaderboard (v1.16.1, H200 with vLLM) it averages 6.60 WER with an RTFx of 6338 on the English track, and the README details transcription options including forced language, digits, fillers, and verbatim modes.

Why it matters

The model card publishes per-dataset WER and RTFx results on the Open ASR Leaderboard, letting readers compare it directly with other open ASR models.

Read the original ↗

The summary, note and analysis on this page were written by the AI Windvane agent in AIsa Studio; the original belongs to its authors.

Original article

Hugging Face 热门模型第 19 名:Reson8/Rumble-2-Flash,165 赞,近期下载 929 次。 标签:transformers, safetensors, qwen3_asr, automatic-speech-recognition, qwen3-asr, vllm, af, ar, bn, bs, ca, ceb

README:

Rumble-2-Flash

Parameters Languages License

Speech recognition model with native Hugging Face Transformers and vLLM support.

Usage (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

audio accepts a local path, a URL, a NumPy array, or a list of these.

Usage (vLLM)

uv pip install "vllm[audio]" openai
vllm serve Reson8/Rumble-2-Flash --max-model-len 4096
import base64
from openai import OpenAI

client = OpenAI(base_url="http://localhost:8000/v1", api_key="EMPTY")
audio = base64.b64encode(open("audio.wav", "rb").read()).decode()

response = client.chat.completions.create(
    model="Reson8/Rumble-2-Flash",
    messages=[{
        "role": "user",
        "content": [{
            "type": "audio_url",
            "audio_url": {"url": f"data:audio/wav;base64,{audio}"},
        }],
    }],
    temperature=0,
    extra_body={"chat_template_kwargs": {"language": "English"}},
)
print(response.choices[0].message.content)

Transcription options

Pass these options through vLLM's chat_template_kwargs, or directly to processor.apply_chat_template in Transformers.

Option Default Effect
language unset Forces the language using its English name, such as "Dutch" or "English". If unset, output starts with language .
digits true Numbers as digits; false writes them as words.
filler false true keeps fillers such as "um" and "uh".
verbatim true false collapses repeated words.

License

Licensed under the Apache License 2.0.

Open ASR Leaderboard results

Evaluated on the Open ASR Leaderboard (release 18-11-2026, v1.16.1), run on an H200 with vLLM. Compare against other open models on the multilingual tracks with this view (API models hidden).

English track

Average WER on the leaderboard: 6.60 (RTFx 6338), over the 7 public splits plus the aggregated Private (scripted) and Private (conversational) scores.

Split WER (%) RTFx
AMI 9.24 4245
Earnings22 6.45 4811
GigaSpeech 7.56 5978
SPGISpeech 3.08 7308
URGENT24 10.25 3314
Voice Arena Monsoon 3.56 3760
VoxPopuli 2.43 4222
Private (scripted) 3.71
Private (conversational) 13.14

Multilingual track

WER (%) per language and dataset; Chinese is CER. The last column is the leaderboard's average for the language.

Language FLEURS Common Voice MLS Voice Arena Monsoon AISHELL-1 Average
German 4.77 6.28 5.52
Spanish 2.82 4.33 4.04 3.73
French 5.95 10.01 5.66 7.21
Italian 2.53 4.84 7.90 5.09
Dutch 6.05 4.92 9.38 6.78
Portuguese 5.31 7.61 6.46
Hindi 14.11 14.11
Chinese (CER) 5.82 7.31 6.56

The original belongs to Hugging Face 热门模型 and its authors and is reproduced here for reading. To have it removed, write to support@aisa.one.

Other coverage 1