Downloads · 30 days
16
18% of all-time downloads
nvidia-ca-conformer-ctc-large-onnx
OpenVoiceOS/nvidia-ca-conformer-ctc-large-onnx
nvidia-ca-conformer-ctc-large-onnx is a automatic speech recognition model from OpenVoiceOS. Use it when you need speech turned into text. It is set up for onnx-asr. The card lists the license as cc-by-4.0.
ASR model exported to ONNX for the onnx-asr library and the ovos-stt-plugin-onnx-asr OpenVoiceOS STT plugin. Ships both fp32 and int8 weights.
All-time downloads
89
Public
Repo size
651 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx_data506 MB · 78%
At a glance
- Task
- Automatic Speech Recognition
- Library
- onnx-asr
- License
- cc-by-4.0
- Model type
- nemo-conformer-ctc
- Access
- Public
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026
- SHA
- e83d7891
Base models
Model card
From the Hugging Face model README
nvidia-ca-conformer-ctc-large-onnx
ASR model exported to ONNX for the onnx-asr library and the ovos-stt-plugin-onnx-asr OpenVoiceOS STT plugin. Ships both fp32 and int8 weights.
Language: Catalan. Converted from nvidia/stt_ca_conformer_ctc_large.
import onnx_asr
model = onnx_asr.load_model("OpenVoiceOS/nvidia-ca-conformer-ctc-large-onnx")
print(model.recognize("audio.wav"))
- Task
- Automatic Speech Recognition
- Library
- onnx-asr
- Type
- nemo-conformer-ctc
- License
- cc-by-4.0
- Languages
- ca
- Created
- Jul 4, 2026
- Updated
- Jul 4, 2026