{"v":1,"id":"model:hf:nvidia/parakeet-ctc-1.1b","slug":"model-nvidia-parakeet-ctc-1-1b","kind":"model","category":"speech","title":"parakeet-ctc-1.1b","summary":"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 […","source":{"provider":"hf","ref":"nvidia/parakeet-ctc-1.1b","url":"https://huggingface.co/nvidia/parakeet-ctc-1.1b","rev":"20e63a0fed6aedba145b74b826dbd41df0941730","fetchedAt":"2026-10-02T20:52:20.301Z","etag":"W/\"246d-7lSNP75/qR/37epf+wuq90vi5Dg\""},"author":{"name":"nvidia","url":"https://huggingface.co/nvidia"},"license":{"spdx":"cc-by-4.0","raw":"cc-by-4.0","open":true},"metrics":{"downloads":317747,"likes":61,"stars":18539,"openIssues":325,"lastRelease":{"tag":"v3.0.0","at":"2026-08-07T00:13:21Z"},"pushedAt":"2026-10-02T16:11:38Z","takenAt":"2026-10-02T20:52:20.301Z"},"tags":["nemo","safetensors","gguf","parakeet_ctc","automatic-speech-recognition","transformers","speech","audio","FastConformer","Conformer","pytorch","NeMo","hf-asr-leaderboard","ctc","en","dataset:librispeech_asr","dataset:fisher_corpus","dataset:Switchboard-1","dataset:WSJ-0","dataset:WSJ-1","dataset:National-Singapore-Corpus-Part-1","dataset:National-Singapore-Corpus-Part-6","dataset:vctk","dataset:voxpopuli","dataset:europarl","dataset:multilingual_librispeech","dataset:mozilla-foundation/common_voice_8_0","dataset:MLCommons/peoples_speech","model-index","eval-results","deploy:azure"],"pipeline":"automatic-speech-recognition","links":{"github":"NVIDIA-NeMo/Speech"},"updatedAt":"2026-08-05T21:47:03.000Z","collectedAt":"2026-10-02T20:52:20.301Z","review":{"numbers":["317,747 downloads on Hugging Face","61 likes","license cc-by-4.0","1.1 GB for parakeet-ctc-1.1b.q8_0.gguf","18,539 stars on NVIDIA-NeMo/Speech","325 open issues and PRs","last release v3.0.0 on 2026-08-07"],"log":null},"trust":"unlabeled","health":{"status":"alive","checkedAt":"2026-10-02T20:52:20.301Z","http":200},"description":"# Parakeet CTC 1.1B (en)\n\nimg {\n display: inline;\n}\n\n[](#model-architecture)\n| [](#model-architecture)\n| [](#datasets)\n\n`parakeet-ctc-1.1b` is an ASR model that transcribes speech in lower case English alphabet. This model is jointly developed by [NVIDIA NeMo](https://github.com/NVIDIA/NeMo) and [Suno.ai](https://www.suno.ai/) teams.\nIt is an XXL version of FastConformer CTC [1] (around 1.1B parameters) model.\nSee the [model architecture](#model-architecture) section and [NeMo documentation](https://docs.nvidia.com/deeplearning/nemo/user-guide/docs/en/main/asr/models.html#fast-conformer) for complete architecture details.\n\n## NVIDIA NeMo: Training\n\nTo train, fine-tune or play with the model you will need to install [NVIDIA NeMo](https://github.com/NVIDIA/NeMo). We recommend you install it after you've installed latest PyTorch version.\n```\npip install nemo_toolkit['all']\n``` \n\n## How to Use this Model\n\nThere are several ways to use this model. Choose the one that fits your needs.\n\n### Run locally with NeMo-Speech.cpp\n\n[NeMo-Speech.cpp](https://github.com/NVIDIA/NeMo-Speech.cpp) provides a\nlightweight native C++ runtime for local inference with\nthis model. After [installing the runtime](https://github.com/NVIDIA/NeMo-Speech.cpp#installation):\n\n```bash\nhf download nvidia/parakeet-ctc-1.1b \\\n  parakeet-ctc-1.1b.q8_0.gguf \\\n  --local-dir models\n\nnemo-speech transcribe audio.wav \\\n  --model models/parakeet-ctc-1.1b.q8_0.gguf\n```\n\nSee the [NeMo-Speech.cpp documentation](https://github.com/NVIDIA/NeMo-Speech.cpp)\nfor more details.\n\n### NVIDIA NeMo\n\nThe model is available for use in the NeMo toolkit [3], and can be used as a pre-trained checkpoint for inference or for fine-tuning on another dataset. Moreover, you can now run Parakeet CTC natively with [Transformers](https://github.com/huggingface/transformers) 🤗.\n\n#### Automatically instantiate the model\n\n```python\nimport nemo.collections.asr as nemo_asr\nasr_model =…\n\nSource: https://huggingface.co/nvidia/parakeet-ctc-1.1b","install":{"kind":"model","hfId":"nvidia/parakeet-ctc-1.1b","gated":false,"format":"gguf","files":[{"name":"model.safetensors","size":4250698604,"sha256":"57e0bc26772f3360b7ae0c087f184364179906674d08fc8b71d48a54d4f52145"},{"name":"parakeet-ctc-1.1b.q8_0.gguf","size":1178100960,"quant":"Q8_0","sha256":"6584fc0fdacf1c220401ea4c3a1d5b44454b655c141cb8672178072c203d92b8"}],"totalBytes":5428799564,"suggestedFile":"parakeet-ctc-1.1b.q8_0.gguf","requirements":{"ramGb":2,"diskBytes":1178100960,"note":"estimate: suggested file size × 1.15 + 0.5 GB; a real measurement comes with lsh models"},"runWith":["whisper.cpp"],"command":"lsh models install hf:nvidia/parakeet-ctc-1.1b"}}