whatmodel.sh / stt / Parakeet TDT-CTC 1.1B

Parakeet TDT-CTC 1.1B

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

Parakeet TDT-CTC 1.1B is an open-weights speech-to-text model from NVIDIA, released May 2024. Its published size is 1.071B parameters. Licence: cc-by-4.0.

Catalogue identity notes

nvidia/parakeet-tdt_ctc-1.1b ('Parakeet TDT-CTC 1.1B PnC(en)', hybrid FastConformer TDT-CTC XXL, English with punctuation and capitalisation; jointly developed by NVIDIA NeMo and Suno.ai per card). Distinct from parakeet-tdt-1-1b and parakeet-tdt-ctc-110m (catalogued). transcribe.cpp port pins upstream 675e786 (2025-02-18, current main); repo created 2024-05-07.

Model information sources

Release date ↗ · Parameter count ↗

transcribe.cpp catalog 'params' 1,070,516,870 for its converted port of nvidia/parakeet-tdt_ctc-1.1b@675e786 (no safetensors index on the Hugging Face repo).

55.9±3.9#62 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 TDT-CTC 1.1B, out of 176 with a score, then more from NVIDIA.

#modelscorewhereRAMreleased
71Orukeet Oruk AI57±4local~0.7GB2026-09
72Zipformer Transducer XL 290M SoundsGood AI56±5comparison only2026-05
73Parakeet TDT-CTC 1.1B NVIDIA56±4local~1.3GB2024-05
74GPT-4o Mini Transcribe OpenAI56±2api $0.0030/audio min2025-03
75Omnilingual ASR LLM 1B v2 Meta56±3local~6GB2025-12
more from NVIDIA
28Canary-Qwen-2.5B NVIDIA61±2local~6.6GB2025-07
35Parakeet TDT 0.6B v2 NVIDIA60±1local~1.9GB2025-05
37Parakeet Unified EN 0.6B NVIDIA60±4local~0.7GB2026-04

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 WER1.9% ✎▁···▁▁▂·▄▄██ beats 31/56avg 2.3%▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇▇ 67%blunt
FLEURS English test WER4.7% ✎▁··▁▁▁▁▁▁▃█▁ beats 31/56avg 5.8%▇▇▇▇▇▇▇▇▇▇▇ 27%blunt

$ where to run it

Other ways to run it

  1. Run it as published · needs ~1.27 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-tdt_ctc-1.1b-gguf parakeet-tdt_ctc-1.1b-Q8_0.gguf --local-dir models/parakeet-tdt_ctc-1.1b && build/bin/transcribe-cli -m models/parakeet-tdt_ctc-1.1b/parakeet-tdt_ctc-1.1b-Q8_0.gguf audio.wav

Official weights and documentation: huggingface.co/nvidia ↗

$ 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= 55.9

$ 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