Instructions to use OpenVoiceOS/nvidia-be-conformer-transducer-large-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use OpenVoiceOS/nvidia-be-conformer-transducer-large-onnx with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("OpenVoiceOS/nvidia-be-conformer-transducer-large-onnx") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7c16af4b5f7abe7c33a1630b4cd5521a0940dda097a3767d678a5e4d7daa5f99
- Size of remote file:
- 21.3 MB
- SHA256:
- f4a5efd167ec41f3e879e0ebfa5dbb759b694975fea08726480a385e54422eb2
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.