Zipformer cr CTC Transducer XL 290M
Sounds Good AI · released Jul 9, 2026 · soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M
Speech to textTranscribes a recording into words
- Type
- Open weightsCreative Commons Attribution-NonCommercial 4.0
- Languages
- 1
- Size
- 0.3B
Context measured in tokens · download allowed, licence restricts use
Our take
Written Sep 5, 2026Zipformer cr CTC Transducer XL is a 290-million-parameter speech-to-text model released in July 2026. It excels at transcribing accented earnings calls and meeting-room audio, though its non-commercial licence and lack of hosted providers limit who can use it.
Pick this for accented earnings-call transcription or meeting-room audio where accuracy matters, or for fast batch processing at about 160 times real-time. Use it in research and non-commercial projects under its CC BY-NC 4.0 licence. Skip it if you need commercial deployment, podcast or video transcription, or a hosted API.
The case for it
- Among the most accurate on accented earnings-call audio, at 7.6% word error — near the top of the field.
- Competitive on meeting-room recordings, at 10.3% word error, better than most models.
- Very fast: about 160 times real-time on benchmark hardware.
- Strong on clean read-aloud audio, at 1.3% word error.
The case against it
- Falls behind on podcasts and video, at 8.3% word error — worse than most.
- Non-commercial licence prohibits commercial use and enterprise deployment.
- No hosted inference options available; you must run it yourself.
How good is it?
TranscriptionTurning speech into text3 of 5Open ASR WER · 43rd of 76
94.7%
Misses roughly one word in 19, averaged over nine English test sets.
158×62nd of 74
an hour of audio in 23 seconds, 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. 21.4 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. 22.6 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. 4.6 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Zipformer cr CTC Transducer XL 290M 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 allowsCreative Commons Attribution-NonCommercial 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
Creative Commons Attribution-NonCommercial 4.0
Weights are downloadable but commercial use is prohibited. Research and personal use only.
Identifiers
- Hugging Face
- soundsgoodai/Zipformer-cr-ctc-transducer-XL-290M
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- soundsgoodai-zipformer-cr-ctc-transducer-xl-290m