Automatic Speech Recognition
ONNX
NeMo
English
asrjs/speech-recognition
speech
audio
onnxruntime
asrjs
NeMo
FastConformer
RNNT
streaming-asr
eou
end-of-utterance
parakeet
voice-agent
Instructions to use thoratsr7/parakeet-realtime-eou-120m-v1-onnx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use thoratsr7/parakeet-realtime-eou-120m-v1-onnx with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("thoratsr7/parakeet-realtime-eou-120m-v1-onnx") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
| { | |
| "model_id": "nvidia/parakeet_realtime_eou_120m-v1", | |
| "sample_rate": 16000, | |
| "mel_bins": 128, | |
| "frame_shift_seconds": 0.01, | |
| "subsampling_factor": 8, | |
| "vocab_size": 1026, | |
| "blank_id": 1026, | |
| "eou_id": 1024, | |
| "eob_id": 1025, | |
| "pred_hidden": 640, | |
| "pred_layers": 1, | |
| "max_symbols_per_step": 10 | |
| } |