Modelpublic

OpenVoiceOS/primeline-parakeet-onnx

sourceHugging Facecc-by-4.0updated 1mo agoView on Hugging Face

0likes104downloads

Model Card

primeline-parakeet — ONNX

ONNX export of `primeline/parakeet-primeline`, a 600M-parameter German ASR model built on the NVIDIA FastConformer encoder with a Token-and-Duration Transducer (TDT) decoder. The export runs on ONNX Runtime through `onnx-asr`, so transcription needs neither PyTorch nor the NeMo toolkit. Output keeps punctuation and capitalisation.

Usage

python

import onnx_asr

model = onnx_asr.load_model("OpenVoiceOS/primeline-parakeet-onnx")
print(model.recognize("audio.wav"))

The int8 weights load with quantization="int8".

In OpenVoiceOS, select it through `ovos-stt-plugin-onnx-asr`:

json

{
  "stt": {
    "module": "ovos-stt-plugin-onnx-asr",
    "ovos-stt-plugin-onnx-asr": {
      "model": "OpenVoiceOS/primeline-parakeet-onnx"
    }
  }
}

Files

File	Size	Notes
`encoder-model.onnx` + `encoder-model.onnx.data`	2.5 GB	FP32 encoder, weights in one external-data file
`decoder_joint-model.onnx`	73 MB	FP32 decoder + joint network
`encoder-model.int8.onnx`	654 MB	INT8 dynamic, per-channel
`decoder_joint-model.int8.onnx`	18 MB	INT8 dynamic, per-channel
`vocab.txt`		SentencePiece tokens plus the `<blk>` CTC blank
`config.json`		`nemo-conformer-tdt`, 128 mel features, subsampling factor 8

Export

Exported with NeMo ASRModel.restore_from(...) followed by model.export(), which writes the encoder and the fused decoder-joint graph separately. INT8 variants come from ONNX Runtime dynamic quantization with per-channel weights.

Verification

Transcribed five German sentences rendered by gTTS. Both the FP32 and the INT8 variant scored 0% word error rate and reproduced the punctuation and capitalisation of the source text. This is a smoke test on synthetic speech, not a benchmark — for accuracy figures on real corpora see the WER table on the base model card.

License

CC-BY-4.0, inherited from the base model.