Model reference · open weights
parakeet-ctc is an open-weight audio or speech model from nvidia, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Parakeet CTC 1.1B (en) img { display: inline; } [](#model-architecture) 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. NVIDIA NeMo: Training To train, fine-tune or play with the model you will need to install NVIDIA NeMo. We recommend you install it after you've installed latest PyTorch version. How to Use this Model There are several ways to use this model. Choose the one that fits your needs. Run locally with NeMo-Speech.cpp NeMo-Speech.cpp provides a lightweight native C++ runtime for local inference with this model. After installing the runtime: See the NeMo-Speech.cpp documentation for more details. NVIDIA NeMo The 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 🤗. Automatically instantiate the model Transcribing using NeMo First, let's get a sample Then simply do: Transcribing using Transformers 🤗 Make sure to install transformers from source. For more details about usage, the refer to Transformers' documentation. Transcribing many audio files Input This model accepts 16000 Hz mono-channel audio (wav files) as input. Output This model provides transcribed speech as a string for a given audio sample. Model Architecture FastConformer [1] is an optimized version of the Conformer model with 8x depthwise-separable convolutional downsampling. The model is trained using CTC loss. You may find more information on the details of FastConformer here: Fast-Conformer Model. Training The NeMo toolkit [3] was used for training the models for over several hundred epochs. These model are trained with this example script and this base config. The tokenizers for these models were built using the text transcripts of the train set with this script. Datasets The model was trained on 64K hours of English speech collected and prepared by NVI
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | nvidia |
|---|---|
| Type | Audio & music |
| Parameters (lead) | 1.1B |
| Variants | 1 |
| Runs with | nemo |
| Released | 2023-12-28 |
| Popularity | 1.7M downloads / month |
| Likes | 58 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| parakeet-ctc-1.1b | 1.1B | BF16 | ~2.4 GB | ✓ | Weights ↗ |
Benchmarks
As published on the model card — the maker's own numbers, not measured by AxForge.
| Task | Dataset | Metric | Score |
|---|---|---|---|
| Automatic Speech Recognition | AMI (Meetings test) | Test WER | 15.62 |
| Automatic Speech Recognition | Earnings-22 | Test WER | 13.69 |
| Automatic Speech Recognition | GigaSpeech | Test WER | 10.27 |
| Automatic Speech Recognition | LibriSpeech (clean) | Test WER | 1.83 |
| Automatic Speech Recognition | LibriSpeech (other) | Test WER | 3.54 |
| automatic-speech-recognition | SPGI Speech | Test WER | 4.2 |
| automatic-speech-recognition | tedlium-v3 | Test WER | 3.54 |
| Automatic Speech Recognition | Vox Populi | Test WER | 6.53 |
| automatic-speech-recognition | Mozilla Common Voice 9.0 | Test WER | 9.02 |
Using it via the API
Once AxForge deploys parakeet-ctc for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (parakeet-ctc below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/audio/transcriptions \ -H "Authorization: Bearer $AXFORGE_API_KEY" \ -F model="parakeet-ctc" -F file=@audio.mp3
Licence
Open weights under cc-by-4.0 — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗