visualears-fastconformer-fa-full-ab-FP16.nemo: FP16 NeMo checkpoint.
validation/fp16_vs_base_eval_summary.json: comparison summary.
validation/fp16_eval_predictions.jsonl: FP16 predictions for the 200-clip eval slice.

Usage

python

import nemo.collections.asr as nemo_asr

model = nemo_asr.models.ASRModel.restore_from("visualears-fastconformer-fa-full-ab-FP16.nemo").cuda().eval()
transcripts = model.transcribe(["clip.wav"])
print(transcripts[0])

Notes

This is a reduced-precision checkpoint for NVIDIA/NeMo experimentation. The exact transcript-parity metric is normalized transcript equality on the fixed 200-clip FLEURS-fa slice, not logit-level equality.

Reza2kn/visualears-fastconformer-fa-full-ab-fp16

visualears-fastconformer-fa-full-ab-fp16

Eval — Reza2kn/persian-asr-eval-v0 FLEURS-fa Slice

Files

Usage

Notes

Reza2kn/
visualears-fastconformer-fa-full-ab-fp16

Eval — `Reza2kn/persian-asr-eval-v0` FLEURS-fa Slice