whatmodel.sh / stt / Granite Speech 4.1 2B Plus

Granite Speech 4.1 2B Plus

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Granite Speech 4.1 2B Plus is an open-weights speech-to-text model from IBM, released April 2026. Its published size is 2.112B parameters. Licence: apache-2.0.

Catalogue identity notes

ibm-granite/granite-speech-4.1-2b-plus: granite-speech-4.1-2b with speaker-attributed ASR and word timestamps (card: 'has similar capabilities to the Granite-Speech-4.1-2B model. The plus model adds two new community-requested rich transcription features'). transcribe.cpp port pins upstream edd3bf5 (2026-04-29); later commits 56cc51b (README) and 1454e6e (model.sig) do not change weights per their titles. Repo created 2026-04-16.

Model information sources

Release date ↗ · Parameter count ↗

Hugging Face safetensors metadata total 2,111,812,956 (current main 1454e6e); transcribe.cpp catalog counts 2,111,899,452 for the converted port.

60.6±3.9#29 of 162 speech-to-text modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

Score within the Open ASR English short-form WER (March 2026) comparison set only.

$ how it compares

The speech-to-text models ranked either side of Granite Speech 4.1 2B Plus, out of 176 with a score, then more from IBM.

#modelscorewhereRAMreleased
32Voxtral Small 24B (2507) Mistral61±2api $0.0040/audio min +local~59GB2025-07
33Gemini 3.5 Transcribe Live Google61±3api $0.0090/audio min2026-08
34Granite Speech 4.1 2B Plus IBM61±4local~2.4GB2026-04
35Parakeet TDT 0.6B v2 NVIDIA60±1local~1.9GB2025-05
36Tencent Hy-ASR-3.0-preview Tencent60±4comparison only
more from IBM
15Granite Speech 5.0 470M TurboCTC NC IBM64±4local~0.5GB2026-08
18Granite Speech 4.1 2B IBM62±3local~6GB2026-04
19Granite 4.0 1B Speech IBM62±3local~6GB2026-03

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER1.5% ✎▁···▁▁▂·▄▄██ beats 47/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%blunt
FLEURS English test WER4.5% ✎▁··▁▁▁▁▁▁▃█▁ beats 37/56avg 5.8%▇▇▇▇▇▇▇▇▇▇▇ 27%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~2.35 GB · from github.com/handy-computer
    git clone https://github.com/handy-computer/transcribe.cpp.git && cd transcribe.cpp && cmake -B build && cmake --build build && hf download handy-computer/granite-speech-4.1-2b-plus-gguf granite-speech-4.1-2b-plus-Q8_0.gguf --local-dir models/granite-speech-4.1-2b-plus && build/bin/transcribe-cli -m models/granite-speech-4.1-2b-plus/granite-speech-4.1-2b-plus-Q8_0.gguf audio.wav

Weights and documentation: huggingface.co/ibm-granite ↗

$ how the score was worked out · transcribe.cpp model catalog… 94%

Each result implies a score on its own, after adjusting for how hard its test is and who ran it. The score is their weighted average, with a small pull toward the middle for thinly tested models. Each test's weight is its counts column above; here it's added up by who ran the tests. How it works

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%MIT
prior · pull toward the middle▇▇ 6%
weighted average= 60.6

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Use a short GitHub form or edit the data through a pull request. Every number needs a source; here's which ones we can use.

data updated · sources and licences · json