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
File size: 320 Bytes
23ce103 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | {
"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
} |