CoolFace
Modelpublic

OpenVoiceOS/stt_uk_citrinet_1024_gamma_0_25_onnx

sourceHugging Facecc-by-4.0updated 2mo agoView on Hugging Face
0likes31downloads
Model Card

sttukcitrinet1024gamma025_onnx

Ukrainian speech-to-text model. ONNX export of stt_uk_citrinet_1024_gamma_0_25 — an NVIDIA NeMo Citrinet CTC model — for onnx-asr. Runs offline with ONNX Runtime; PyTorch and NeMo are not required.

Part of the OpenVoiceOS STT/ASR ONNX collection.

Files

FilePurpose
model.onnxEncoder + CTC head, fp32
vocab.txtToken vocabulary (<token> <id> per line, ▁ = space, <blk> = CTC blank)
config.jsononnx-asr metadata: model_type: nemo-conformer-ctc, features_size: 80, subsampling_factor: 8

There is no int8 variant: these architectures are convolution-dominated, and dynamic quantization produces ConvInteger nodes that ONNX Runtime cannot execute on CPU. int8 requires static QDQ quantization with calibration data.

Usage

With onnx-asr (pip install onnx-asr[cpu,hub]):

python
import onnx_asr

model = onnx_asr.load_model("OpenVoiceOS/stt_uk_citrinet_1024_gamma_0_25_onnx")
print(model.recognize("speech.wav"))  # 16 kHz PCM wav

With OpenVoiceOS, through ovos-stt-plugin-onnx-asr (mycroft.conf):

json
{
  "stt": {
    "module": "ovos-stt-plugin-onnx-asr",
    "ovos-stt-plugin-onnx-asr": {
      "model": "OpenVoiceOS/stt_uk_citrinet_1024_gamma_0_25_onnx"
    }
  }
}

Export and verification

Exported from the original checkpoint with NeMo's model.export() (see the conversion guide). The subsampling_factor was measured empirically on the exported graph, and the export was verified differentially: the ONNX model and the original NeMo checkpoint produce identical transcriptions on a reference clip.

Accuracy, training data and limitations

See the source model card for benchmark results, training corpora and known limitations. This repo changes the runtime, not the weights.

Related projects