whatmodel.sh / stt / Whisper large (v1)
Whisper large (v1)
↗ share
+ contribute
Whisper large (v1) is an open-weights speech-to-text model from OpenAI, released September 2022. Its published size is 1.55B parameters. Licence: apache-2.0.
Catalogue identity notes
Exact checkpoint openai/whisper-large (openai-whisper name 'large-v1'; the HF repo openai/whisper-large is the original v1 large model, distinct from large-v2 and large-v3). Params from the Whisper README size table. Licence as declared on the HF card.
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 Whisper large (v1), out of 176 with a score, then more from OpenAI.
| # | model | score | where | ||
|---|---|---|---|---|---|
| 115 |  Multitalker Parakeet Streaming 0.6B v1 | 50±4 | local | ||
| 116 |  Omnilingual ASR CTC 1B v2 | 50±3 | local | ||
| 117 | Whisper large (v1) | 49±2 | local | ||
| 118 |  OWSM-CTC v3.2 ft 1B | 49±4 | local | ||
| 119 | Nemotron Speech Streaming EN 0.6B | 49±4 | local | ||
| more from OpenAI | |||||
| 13 | GPT Transcribe | 64±4 | api $0.0045/audio min | ||
| 48 | GPT-Realtime-Whisper | 59±3 | api $0.017/audio min | ||
| 61 | Whisper large-v3-turbo | 57±1 | api $0.0005/audio min +local | ||
see all speech-to-text models · find the ones that fit your machine
$ what it's good at
long-form transcription▁▁▄▁·▁▂█▄▁▁▁ #11 of 27 * · 21% of its score · 1 test
Beats Chirp 3, Parakeet TDT 1.1B, Parakeet RNNT 1.1B here, though they rank higher overall.
| test | result | vs the others in its run | counts |
|---|---|---|---|
| Open ASR English long-form WER | 9.4% ✎ | ▁▁▅▁·▃▅█▆▁▂▂ beats 17/30 | 21% |
other tests6 not in a task · 77% of its score
| test | result | vs the others in its run | counts |
|---|---|---|---|
| LibriSpeech test-clean WER | 2.7% ✎ | ▁···▁▁▂·▄▄██ beats 13/56 | 26% |
| Open ASR English short-form WER (March 2026) | 7.9% ✎ | ▁▁▁▃··▁▁▂██▆ beats 37/86 | 21% |
| FLEURS English test WER | 4.5% ✎ | ▁··▁▁▁▁▁▁▃█▁ beats 38/56 | 11% |
| FLEURS Mandarin test error rate | 19.3% ✎ | ▂▂··▂▄▂▂·▆██ beats 3/17 | 10% |
| Open Universal Arabic ASR Leaderboard · 6-test-set average WER | 42.6% ✎ | ▃·▂▂▅█▅▃▂▅▂▂ beats 5/22 | 6.0% |
| AfriSpeech-200 test (108 African accents) · WER | 30.6% ✎ | ███····█████ beats 7/7 | 3.3% |
$ where to run it
Other ways to run it
version
- Run it as published · needs ~4.22 GB · from github.com/openai (official)
uvx --from openai-whisper whisper audio.mp3 --model large-v1
Official weights and documentation: huggingface.co/openai ↗
$ how the score was worked out · transcribe.cpp model catalog… 47%, Open ASR Leaderboard 41%, Open Universal Arabic ASR Lea… 6% and 1 more
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
| source | results | share of the score |
|---|---|---|
 transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports | 3 | 47% |
 Open ASR Leaderboard | 2 | 41% |
| Open Universal Arabic ASR Leaderboard (Elm Research Center) | 1 | 6% |
 AfriSpeech-200 (arXiv:2310.00274v1) · zero-shot WER of open ASR models on African-accented English | 1 | 3% |
| prior · pull toward the middle | 2% | |
| weighted average | = 49.4 |
$ improve this page
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