whatmodel.sh / stt / Granite Speech 3.3 8B

Granite Speech 3.3 8B

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

Granite Speech 3.3 8B is an open-weights speech-to-text model from IBM, released June 2025. Its published size is 8.65B parameters. Licence: apache-2.0.

Catalogue identity notes

Exact checkpoint ibm-granite/granite-speech-3.3-8b (current revision 3.3.2; card 'Release Date: June 19, 2025'; repo first created 2025-04). Params: HF safetensors total. vLLM flags from the card (speech LoRA).

59.4±4.9#37 of 162 speech-to-text modelsfrom 2 benchmark results across 2 sources* 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 3.3 8B, out of 176 with a score, then more from IBM.

#modelscorewhereRAMreleased
43Deepgram Nova 2 Deepgram60±4api $0.0058/audio min2023-09
44Fun-ASR-Flash Alibaba59±4comparison only
45Granite Speech 3.3 8B IBM59±5local~21GB2025-06
46Voxtral Mini Transcribe V2 Mistral59±3api $0.0030/audio min2026-02
47Avalon v1 (en) Aqua Voice59±5comparison only2025-08
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 · 91% of its score
testresultvs the others in its rundifficultycountswhy
Open ASR English short-form WER (March 2026)5.7% ✎▁▁▁▃··▁▁▂██▆ beats 82/86avg 8.2%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%blunt
Speech Accessibility Project dysarthric speech · zero-shot WER (rated subset, N=11,218)23.7% ✎▂·▂··▃····▆█ beats 2/9avg 18%▇▇▇▇ 9.4%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~21.26 GB, NVIDIA only · from huggingface.co/ibm-granite
    vllm serve ibm-granite/granite-speech-3.3-8b --max-model-len 2048 --enable-lora --lora-modules speech=ibm-granite/granite-speech-3.3-8b --max-lora-rank 64

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

$ how the score was worked out · Open ASR Leaderboard 82%, Dysarthric ASR with clinical… 9%

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
Open ASR Leaderboard1▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 82%Apache-2.0
Dysarthric ASR with clinical context on the Speech Accessibility Project (arXiv:2605.02782v2)1▇▇▇ 9%CC BY 4.0
prior · pull toward the middle▇▇▇ 9%
weighted average= 59.4

$ 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