Hojo ASR V1
Hojo AI · released May 24, 2026 · HojoAI/Hojo-ASR-V1
Speech to textTranscribes a recording into words
- Type
- Open weightsApache License 2.0
- Languages
- 2
- Size
- 5.2B
Context measured in tokens
Our take
Written Sep 17, 2026Hojo ASR V1 is a speech-to-text model you can download and run yourself, and it is among the most accurate we list on podcast and video audio. It is fast enough to clear a backlog, but every accuracy figure we hold is English only.
Reach for it for podcasts, video or everyday internet audio, run on your own machine under a licence that allows commercial use, changes and redistribution. It also suits a long backlog, since an hour of audio takes about 50 seconds on the leaderboard's own hardware. Skip it if you need speaker labelling, timestamps or streaming, or accurate transcription in a language other than English.
The case for it
- Among the most accurate we list on podcast and video audio: 6.1% of words wrong, which is the best any model achieves on that condition, against a field middle of 8.3%.
- Strong on the hard cases too, at 7% of words wrong on accented speech and 7.5% on meeting recordings, both better than most models on those conditions.
- Fast enough to work through a backlog: 72.5 times real time, so an hour of audio in about 50 seconds on the leaderboard's own hardware.
- The licence allows commercial use, changes and redistribution (Apache License 2.0).
The case against it
- Every accuracy figure we hold is English only, so non-English work needs a trial on your own recordings.
- Word error rate counts words recognised, not who said them: speaker labelling, timestamps and streaming are not measured here.
- We list no host for it, so running it yourself is the only route we can point you to.
How good is it?
An open speech-to-text model for turning recordings of meetings, podcasts and everyday speech into written text.
- turning spoken English into written textOpen ASR WER · 11th of 76
- transcribing recordings of meetings in a roomRecorded meetings · 15th of 92
- transcribing podcasts and video audioPodcasts and video · 1st of 92
TranscriptionTurning speech into text4 of 5Open ASR WER · 11th of 76
95.7%
Misses roughly one word in 23, averaged over nine English test sets.
72.5×72nd of 74
an hour of audio in 50 seconds, on the board's own hardware. Your machine will differ.
2
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.
Which languages ↓ ↑
Chinese · English
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. 18.1 GB spare means a 10% error in the size would not change the answer.
GeForce RTX 5090 · 32 GB
Room to spare. 26.1 GB spare means a 10% error in the size would not change the answer.
Apple M2 (8-core GPU, 8GB unified) · 8 GB
Room to spare. 1.3 GB spare means a 10% error in the size would not change the answer.
These cards answer whether Hojo ASR V1 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
- HojoAI/Hojo-ASR-V1
- Takes in, gives back
- Audio in, text out
- Catalogue slug
- hojoai-hojo-asr-v1