whatmodel.sh / stt / Parakeet primeline (German)

Parakeet primeline (German)

+ contribute
Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

Parakeet primeline (German) is an open-weights speech-to-text model from primeLine, released December 2025. Its published size is 0.627B parameters. Licence: cc-by-4.0.

Catalogue identity notes

primeline/parakeet-primeline: German-optimised fine-tune of nvidia/parakeet-tdt-0.6b-v3 (card: 'based on the NVIDIA parakeet-tdt-0.6b-v3 architecture', 'specifically optimized for high-precision German transcription', 600M). transcribe.cpp port pins upstream 3f1a9bc (2026-04-24, current main; checkpoint file 2_95_WER.nemo). Repo created 2025-12-10. Also run by raven.eval (Tuda-De, MLS, CV19) - different sets, not imported.

Model information sources

Release date ↗ · Parameter count ↗

transcribe.cpp catalog 'params' 627,052,166 for its converted port of primeline/parakeet-primeline@3f1a9bc (no safetensors index on the Hugging Face repo).

52.5±3.9#86 of 162 speech-to-text modelsfrom 2 benchmark results across 1 source* thinly tested, treat the rank as provisional

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 Parakeet primeline (German), out of 176 with a score.

#modelscorewhereRAMreleased
95LiteWhisper large-v3-turbo-acc Efficient-Speech (LiteASR)53±4local~2.1GB2025-02
96Voxtral Mini 4B Realtime (2602) Mistral53±2api $0.0060/audio min +local~3.2GB2026-02
97Parakeet primeline (German) primeLine53±4local~0.7GB2025-12
98Omnilingual ASR CTC 7B v2 Meta52±3local~16GB2025-12
99Omnilingual ASR LLM 300M Meta52±2local~4.4GB2025-11

see all speech-to-text models · find the ones that fit your machine

$ what it's good at

other tests2 not in a task · 94% of its score
testresultvs the others in its rundifficultycountswhy
LibriSpeech test-clean WER2.2% ✎▁···▁▁▂·▄▄██ beats 20/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%blunt
FLEURS English test WER4.8% ✎▁··▁▁▁▁▁▁▃█▁ beats 29/56avg 5.8%▇▇▇▇▇▇▇▇▇▇▇ 27%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~0.74 GB · from github.com/handy-computer
    git clone https://github.com/handy-computer/transcribe.cpp.git && cd transcribe.cpp && cmake -B build && cmake --build build && hf download handy-computer/parakeet-primeline-gguf parakeet-primeline-Q8_0.gguf --local-dir models/parakeet-primeline && build/bin/transcribe-cli -m models/parakeet-primeline/parakeet-primeline-Q8_0.gguf audio.wav

Official weights and documentation: huggingface.co/primeline ↗

$ how the score was worked out · transcribe.cpp model catalog… 94%

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

sourceresultsshare of the scorelicence
transcribe.cpp model catalog · LibriSpeech test-clean WER of validated full-precision ports2▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 94%MIT
prior · pull toward the middle▇▇ 6%
weighted average= 52.5

$ improve this page

Update model informationAdd a place to run itAdd a test resultPropose a benchmarkCorrect a benchmark scoreEdit data on GitHub

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