Automatic Speech Recognition
NeMo
PyTorch
English
speech
streaming
audio
Transducer
Conformer
CTC
NeMo
Eval Results (legacy)
Instructions to use nvidia/stt_en_fastconformer_hybrid_large_streaming_multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/stt_en_fastconformer_hybrid_large_streaming_multi with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/stt_en_fastconformer_hybrid_large_streaming_multi") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Future streaming model plans?
6
#1 opened over 2 years ago
by
dave-savati