Granite Speech 5.0 470m Turboctc
IBM · released Aug 4, 2026 · ibm-granite/granite-speech-5.0-470m-turboctc
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 1
- Size
- 0.5B
Context measured in tokens
Our take
Written Sep 11, 2026Granite Speech 5.0 Turboctc is a tiny downloadable speech-to-text model from IBM that turns English audio into text at extreme speed. It is built for challenging audio like meetings and accented speech, though it lags on cleaner material.
Pick this when raw speed matters most — it processes an hour of audio in under a second on benchmark hardware. Use it for meeting-room or accented-speech transcription where it scores better than most models, or for edge deployment where its tiny size and Apache licence fit. Skip it if you need non-English languages, clean-read-aloud accuracy, or a hosted provider — none are available.
The case for it
- Extreme speed: 12,946 times real time on the leaderboard's hardware.
- Better than most on accented earnings calls and recorded meetings with crosstalk.
- Apache 2.0 licence allows commercial use, modification and redistribution.
- Only 0.5B parameters, small enough for low-resource or edge deployment.
The case against it
- Worse than most on clean read-aloud and internet audio like podcasts and video.
- English only; no measured accuracy in other languages.
- No hosted offers listed; you must run it yourself.
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 · 17th of 92
TranscriptionTurning speech into text3.5 of 5Open ASR WER · 36th of 76
95%
Misses roughly one word in 20, averaged over nine English test sets.
12,946×5th 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 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 allowsApache License 2.0, 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
Apache License 2.0
Fully permissive: commercial use, redistribution, and derivatives allowed. Requires attribution and a copy of the license. Includes an express patent grant.
Identifiers
- Hugging Face
- ibm-granite/granite-speech-5.0-470m-turboctc
- Architecture
- Dense
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- ibm-granite-granite-speech-5-0-470m-turboctc