README.md

---
language:
- fa
license: apache-2.0
pipeline_tag: automatic-speech-recognition
base_model:
- nvidia/stt_fa_fastconformer_hybrid_large
base_model_relation: finetune
tags:
- automatic-speech-recognition
- persian
- farsi
- nemo
- fastconformer
- rnnt
- ctc
- visualears
library_name: nemo
---

# VisualEars FastConformer Persian ASR Full A+B

Persian/Farsi ASR fine-tune for the small/fast VisualEars model, trained from `nvidia/stt_fa_fastconformer_hybrid_large` on the full A+B training mix.

## Main Checkpoint

- `fa_fastconformer_ab_final.nemo`: final NeMo FastConformer hybrid RNNT/CTC checkpoint from the full A+B run.

## Runtime Exports

Canonical runtime exports live in separate derivative model repos so Hugging Face can attach them to this fine-tune as quantized/export variants:

| Repo | Format | Validation |
| --- | --- | ---: |
| [`visualears-fastconformer-fa-full-ab-onnx-fp`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-onnx-fp) | ONNX FP fixed CTC core | 100.00% CTC argmax parity |
| [`visualears-fastconformer-fa-full-ab-onnx-w4`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-onnx-w4) | ONNX Runtime weight-only 4-bit, asymmetric block-32 | 98.61% CTC argmax parity |
| [`visualears-fastconformer-fa-full-ab-coreml-fp16`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-coreml-fp16) | CoreML FP16 fixed CTC core | 99.85% CTC argmax parity |
| [`visualears-fastconformer-fa-full-ab-coreml-w4`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-coreml-w4) | CoreML 4-bit k-means palettized, compressed variant | 98.06% CTC argmax parity |
| [`visualears-fastconformer-fa-full-ab-coreml-w4-quality`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-coreml-w4-quality) | CoreML 4-bit k-means palettized, quality-first variant | 99.65% CTC argmax parity |
| [`visualears-fastconformer-fa-full-ab-litert-fp`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-litert-fp) | LiteRT/TFLite FP fixed CTC core | 100.00% CTC argmax parity; 100.00% transcript parity on 16 calibration items |
| [`visualears-fastconformer-fa-full-ab-litert-w4`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-litert-w4) | LiteRT/TFLite selected fully-connected weight-only 4-bit | 98.23% frame CTC argmax parity; failed transcript parity at 37.5% on 16 calibration items |
| [`visualears-fastconformer-fa-full-ab-fp16`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-fp16) | NeMo FP16 reduced-precision checkpoint | 98.0% exact transcript match vs FP base on 200 FLEURS-fa eval clips |
| [`visualears-fastconformer-fa-full-ab-fp8`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-fp8) | NeMo FP8 via NVIDIA ModelOpt | 18.48% WER / 6.69% CER on 200 FLEURS-fa eval clips; 99.47% WER retention vs FP base |
| [`visualears-fastconformer-fa-full-ab-nvfp4`](https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab-nvfp4) | NeMo NVFP4 W4A4 via NVIDIA ModelOpt | 20.33% WER / 7.38% CER on 200 FLEURS-fa eval clips |

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

## Training Snapshot

- Train manifest: 6,231,918 rows
- Validation manifest: 31,424 rows
- Final train step: 48,687
- NeMo architecture: FastConformer hybrid RNNT/CTC

## Benchmarks

External benchmark snapshot from June 10, 2026:

| Decoder | Golha gold-69 WER | FLEURS fa WER | FLEURS fa CER |
| --- | ---: | ---: | ---: |
| RNNT greedy | 25.29 | 15.73 | 5.25 |
| CTC + 4-gram LM, alpha=0.2 beta=-1.0 beam=50 | 25.96 | 13.60 | 5.39 |

The LM setting was calibrated on a FLEURS-256 slice and helped FLEURS WER, but did not improve Golha in this snapshot.

## Notes

This is a research checkpoint. Normalization and tokenization choices matter for reported WER/CER.