nvidia / automatic-speech-recognition updated 16 hours ago

parakeet-ctc-1.1b

Name: parakeet-ctc-1.1b
Author: nvidia

parakeet-ctc-1.1b is an ASR model that transcribes speech in lower case English alphabet. This model is jointly developed by NVIDIA NeMo and Suno.ai teams. It is an XXL version of FastConformer CTC [1] (around 1.1B parameters) model. See the model architecture section and NeMo documentation for complete architecture details.

Params

1.1 B

Context

—

Downloads 30d

1.9 M

Likes

Commercial use: allowed cc-by-4.0 Not gated GGUF · SAFETENSORS 1 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days

1.9 M1.5 M

Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

File	Quant	Size	Est. VRAM	Verdict on RTX 4090 · 24 GB
parakeet-ctc-1.1b.q8_0.gguf	Q8_0	1.2 GB	2.0 GB	✅ Runs comfortably
model.safetensors	f32	4.3 GB	5.3 GB	✅ Runs comfortably

Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Architecture: ParakeetForCTC
Parameters: 1.1 B
Tensor type: F32
Vocabulary: 1,025
Licence: cc-by-4.0
First seen on the Hub: 2023-12-28
Training datasets: librispeech_asr, fisher_corpus, Switchboard-1, WSJ-0, WSJ-1, National-Singapore-Corpus-Part-1, National-Singapore-Corpus-Part-6, vctk, voxpopuli, europarl, multilingual_librispeech, mozilla-foundation/common_voice_8_0, MLCommons/peoples_speech
GigaSpeech (reported): 10.27
Vox Populi (reported): 6.53
tedlium-v3 (reported): 3.54
Earnings-22 (reported): 13.69
SPGI Speech (reported): 4.2
AMI (Meetings test) (reported): 15.62
LibriSpeech (clean) (reported): 1.83
LibriSpeech (other) (reported): 3.54
Mozilla Common Voice 9.0 (reported): 9.02
Added to our catalog: 2026-07-28

Compare with

speaker-diarization-3.1 8.9 M whisper-large-v3-turbo 8.7 M whisperkit-coreml 8.3 M speaker-diarization-community-1 5.3 M wav2vec2-large-xlsr-53-portuguese 4.6 M wav2vec2-large-xlsr-53-russian 4.0 M

Appears in

Best open coding models Commercial-use text models Models that fit in 12 GB