HologramHologram
ModelsIndex Nov 20, 2026

Rumble-2-Flash

929173

Reson8 · 509M parameters · 1.4 GB · Apache 2.0

Address
reson8/rumble-2-flash
Held on
Get it
Status
Verified
Base model
…
Lineage
…
Unchanged from base
…
Trending
#16
Downloads, 30 days
929
Weights
1.4 GB
Revision

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

At a glance

Task
Speech recognition
Input
audio
Output
text
Parameters
509M
Architecture
Qwen 3 ASR
Context
64K tokens
Precision
BF16
Format
Safetensors
Library
transformers
License
Apache 2.0Commercial use
Languages
af, ar, bn, bs, ca, ceb, cs, da +37
Released
Oct 2026
Updated
Nov 2026
Likes
129
Downloads, all time
978

Architecture

Layers
14
Hidden size
1,024
Attention
16 heads, grouped query, 8 KV heads
Vocabulary
99,630
Positions
65,536
Tied embeddings
Yes
Audio encoder
qwen3_asr_encoder

Family

Models built on Rumble-2-Flash.

Run it

Loads with Transformers AutoModelForMultimodalLM and AutoProcessor, pinned to the indexed revision.

from transformers import AutoModelForMultimodalLM, AutoProcessor

model = AutoModelForMultimodalLM.from_pretrained("Reson8/Rumble-2-Flash", revision="a0c34287229103b706c670d70791683e34379732")
processor = AutoProcessor.from_pretrained("Reson8/Rumble-2-Flash", revision="a0c34287229103b706c670d70791683e34379732")

Through the hub: the same tools, each file from a source that is up (Hugging Face, ModelScope, IPFS), at this revision. The last line checks every file against the hash the tree names.

export HF_ENDPOINT=https://gethologram.ai
hf download Reson8/Rumble-2-Flash --quiet && hf cache verify Reson8/Rumble-2-Flash

Spaces

Used in 3 Spaces.

Read the full model card

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 <asr_text>.
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

Derived on Nov 19, 2026 from Hugging Face at revision a0c34287, README.md , config.json .