Instructions to use Muno459/fastconformer-quran with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use Muno459/fastconformer-quran with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("Muno459/fastconformer-quran") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
Defined base model: `stt_en_fastconformer_hybrid_large_pc`
Jazak Allah khayr for this, and for the careful review of the benchmark scorer too. I've added base_model: nvidia/stt_en_fastconformer_hybrid_large_pc directly to the card. Your PR branched just before a recent eval-table update, so I applied the change manually to avoid reverting that, but the metadata is now exactly as you proposed. Closing as incorporated. Barakallah feek for the contribution.
Wa ʻalaykum as-salām, and jazāk Allāhu khayran again for the contribution and your careful review of the benchmark scorer. I really appreciate it. One correction for the record: the base model is actually nvidia/stt_ar_fastconformer_hybrid_large_pcd_v1.0 (the Arabic-pretrained FastConformer-Hybrid Large), not the English stt_en_fastconformer_hybrid_large_pc. I have updated the README.md to reflect the correct base. Barakallah feek.