STT/ASR - onnx
Collection
OVOS STT/ASR models for onnx-asr (ONNX runtime). Most ship fp32 + int8 (set quantization: int8 for faster/smaller CPU inference). • 58 items • Updated • 1
nvidia-de-conformer-ctc-large-onnx
NVIDIA NeMo ASR model exported to ONNX for the onnx-asr library and the ovos-stt-plugin-onnx-asr OpenVoiceOS STT plugin.
Converted from nvidia/stt_de_conformer_ctc_large (cc-by-4.0).
Decoder: CTC (model.onnx) — model_type: nemo-conformer-ctc, features_size 80,
subsampling_factor 4.
import onnx_asr
model = onnx_asr.load_model("OpenVoiceOS/nvidia-de-conformer-ctc-large-onnx")
print(model.recognize("audio.wav"))
Or via OpenVoiceOS config:
{"stt": {"module": "ovos-stt-plugin-onnx-asr",
"ovos-stt-plugin-onnx-asr": {"model": "OpenVoiceOS/nvidia-de-conformer-ctc-large-onnx"}}}
- Downloads last month
- -