Instructions to use Reza2kn/visualears-fastconformer-fa-full-ab-fp8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use Reza2kn/visualears-fastconformer-fa-full-ab-fp8 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("Reza2kn/visualears-fastconformer-fa-full-ab-fp8") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
| { | |
| "source_model": "Reza2kn/visualears-fastconformer-fa-full-ab", | |
| "upload_repo": "Reza2kn/visualears-fastconformer-fa-full-ab-fp8", | |
| "artifact": "Reza2kn_visualears-fastconformer-fa-full-ab-FP8.nemo", | |
| "quantization": "FP8 via modelopt.torch.quantization.FP8_DEFAULT_CFG", | |
| "calibration_dataset": "Reza2kn/persian-asr-eval-v0", | |
| "n_cal": 32, | |
| "max_cal_seconds": 15.0, | |
| "eval_dataset": "Reza2kn/persian-asr-eval-v0", | |
| "n_eval": 200, | |
| "wer": 0.1847741433021807, | |
| "cer": 0.06693711967545639, | |
| "wall_seconds": 10.259917259216309, | |
| "per_clip_latency_ms": 51.29958629608154, | |
| "peak_vram_mib": 662.06494140625 | |
| } |