Granite Speech 5.0 470m Turboctc nc
IBM · released Aug 17, 2026 · ibm-granite/granite-speech-5.0-470m-turboctc-nc
Speech to textTranscribes a recording into words
- Type
- Open weightsCC Attribution-NonCommercial-ShareAlike 4.0
- Languages
- 1
- Size
- 0.5B
Context measured in tokens · download allowed, licence restricts use
Our take
Written Sep 11, 2026Granite Speech 5.0 is a tiny English-only speech-to-text model from IBM that processes audio faster than almost anything else in its class. It excels on clean read-aloud and financial call recordings, but its non-commercial licence and sharp drop-off on harder audio limit where it can be used.
Pick this for batch transcription of clean audiobooks or earnings calls where raw throughput matters more than marginal accuracy gains. Use it for meeting-room audio if a seven-percent error rate is acceptable and speed is critical. Skip it if you need commercial deployment rights, non-English languages, or reliable accuracy on podcasts, video or accented speech.
The case for it
- Processes an hour of audio in under a second on the benchmark harness — extreme speed for its size class.
- Strong on clean read-aloud and financial calls, with error rates better than most models in those conditions.
- Respectable on meeting-room audio despite its tiny parameter count, beating the field middle.
The case against it
- Falls apart on podcasts, video and broadly accented speech, trailing most peers in those conditions.
- Non-commercial licence blocks most product use: no commercial deployment, no proprietary derivatives, share-alike required.
- English only; no other language support is verified or measured.
How good is it?
An open speech-to-text model for turning recordings of meetings into written text.
- transcribing recordings of meetings in a roomRecorded meetings · 11th of 92
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 27th of 76
95.2%
Misses roughly one word in 21, averaged over nine English test sets.
12,762×6th of 74
an hour of audio in under a second, on the board's own hardware. Your machine will differ.
1
Listed on the model card. The accuracy above is English only.
Percentage of words wrong on each set, lower better. Bars are scaled to this model's own worst case; the placing beneath each rate is against every model measured on that set.
The figures above come from the Open ASR Leaderboard, an independent public test that runs every model on the same recordings. It is the only measurement of transcription quality we know of, so there are no other scores to show.
Each of these is the same transcription job on a different kind of recording, so together they say where it holds up and where it slips — not how closely it follows an instruction.
Every published score for this model9 scoresEvery figure we hold, from 9 boards, with who ran it and a link to the source — including the boards no rating above is built on.
Can you run it yourself?
Comfortable fit
GeForce RTX 4090 · 24 GB
Room to spare. 21.2 GB spare means a 10% error in the size would not change the answer.
Apple M1 Pro (16-core GPU) · 32 GB
Room to spare. 22.4 GB spare means a 10% error in the size would not change the answer.
Apple M1 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 4.4 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Granite Speech 5.0 470m Turboctc nc loads, not how fast it transcribes. Throughput figures for a transcription model come from its text decoder, so treat this as a fit answer rather than a speed one.
Memory use by level
Against a 24 GB card.
What is quantisation? →This model on every device we track71 devicesThe Q4 build most people download, on each device: what the weights come to, how much context the memory leaves, and whether it runs. Smallest device that runs it first. This is a fit answer: whether it loads, not how fast it transcribes.
When we formed this view
Recent changes
What moved
first indexed by our pipelineEach date is the day we first saw the change, or the day the maker announced it.
What we do not know about this model yet
- We hold no measured file for it, so all 3 sizes on this page are calculated from the parameter count.
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
Licence and identifiers
What the licence allowsCC Attribution-NonCommercial-ShareAlike 4.0, what it allows commercially, and the identifiers you need to pull this model — its Hugging Face repo, our slug and a machine-readable card.
Licence
CC Attribution-NonCommercial-ShareAlike 4.0
Non-commercial use only, and anything you build on it must carry the same license.
Identifiers
- Hugging Face
- ibm-granite/granite-speech-5.0-470m-turboctc-nc
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- ibm-granite-granite-speech-5-0-470m-turboctc-nc