---
language:
- fa
license: apache-2.0
pipeline_tag: automatic-speech-recognition
base_model:
- Reza2kn/visualears-fastconformer-fa-full-ab
base_model_relation: quantized
tags:
- coreml
- fp16
- ctc
- persian
- farsi
- fastconformer
- visualears
- apple
- automatic-speech-recognition
library_name: coreml
---
# VisualEars FastConformer Persian ASR CoreML FP16

Derivative export of [`Reza2kn/visualears-fastconformer-fa-full-ab`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab).

## Artifact

- Format: CoreML FP16 fixed-length acoustic CTC-core export
- Quantization/conversion: FP16 conversion reference; no 4-bit palettization
- Runtime validation: CoreML CPU
- Validation result: 99.85% CTC argmax parity
- Size: 219 MB mlpackage

## Validation

Runtime parity was checked against PyTorch CTC logits on 16 calibration clips padded to 2005 mel frames. The metric is CTC argmax token agreement versus the PyTorch reference logits, not end-to-end WER.

## Usage Boundary

These are fixed-frame acoustic CTC-core exports. They take precomputed log-mel features as `processed_signal`; they are not full raw-audio-to-text pipelines by themselves.

## Notes

Reference CoreML package for Apple runtimes. Input is precomputed log-mel processed_signal.