whatmodel.sh / stt / Granite Speech 5.0 470M TurboCTC

Granite Speech 5.0 470M TurboCTC

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

Granite Speech 5.0 470M TurboCTC is an open-weights speech-to-text model from IBM, released August 2026. Its published size is 0.47B parameters. Licence: apache-2.0.

62.2±3.9#17 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 5.0 470M TurboCTC, out of 176 with a score, then more from IBM.

#modelscorewhereRAMreleased
18Granite Speech 4.1 2B IBM62±3local~6GB2026-04
19Granite 4.0 1B Speech IBM62±3local~6GB2026-03
20Granite Speech 5.0 470M TurboCTC IBM62±4local~1.6GB2026-08
21MAI-Transcribe-1.5 Microsoft AI62±8api $0.0060/audio min2026-06
22Fish Audio Transcribe 1 Fish Audio62±5api $0.0060/audio min
more from IBM
15Granite Speech 5.0 470M TurboCTC NC IBM64±4local~0.5GB2026-08
26Granite Speech 4.1 2B NAR IBM62±4local~2.5GB2026-03
34Granite Speech 4.1 2B Plus IBM61±4local~2.4GB2026-04

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

$ what it's good at

other tests3 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER1.3% ✎▁···▁▁▂·▄▄██ beats 51/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%blunt
FLEURS English test WER4.6% ✎▁··▁▁▁▁▁▁▃█▁ beats 34/56avg 5.8%▇▇▇▇▇▇▇▇▇▇▇ 27%blunt
Granite 5.0 report · Open ASR public 7-set mean WER lab5.7% ✎█···█·····██ beats 3/3avg 11%—not counted yet: no other model in the same run to compare it with

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.63 GB, Mac only · from github.com/Blaizzy
    uvx --from mlx-audio mlx_audio.stt.generate --model ibm-granite/granite-speech-5.0-470m-turboctc --audio audio.wav --output-path out

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= 62.2

not counted (1)

Design of the IBM Granite 5.0 TurboCTC ASR Model (arXiv:2609.20104v1)Granite 5.0 report · Open ASR public 7-set mean WER [correct]5.7%fewer than three models have this test yet, or this source ran it for this model alone

$ 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