Instructions to use PraxySante/ASR-FR-Nemo-V16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use PraxySante/ASR-FR-Nemo-V16 with NeMo:
# tag did not correspond to a valid NeMo domain.
- Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
ASR-FR-Nemo-V16
Model de reconnaissance automatique de la parole (ASR) pour le francais, converti en fp16 pour une inference plus rapide.
Details du modele
- Origine : PraxySante/praxy-fr-asr-fastconformer-lowercase-step2-tok072026
- Precision : fp16 (half precision)
- Langue : francais
- Sample rate : 16000 Hz
- Encoder layers : None
- WER : 7.03%
Utilisation
from nemo.collections.asr.models import ASRModel
# Load the fp16 model
asr_model = ASRModel.from_pretrained(
"praxysante/ASR-FR-Nemo-V16",
strict=False
)
# Transcribe audio
text = asr_model.transcribe(["audio.wav"])
print(text)
Performance
Le modele converti en fp16 offre une inference plus rapide tout en maintenant une qualite de transcription similaire.
- Downloads last month
- 14
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support