Reza2kn / visualears-fastconformer-fa-full-ab

huggingface.co
Total runs: 354
24-hour runs: 0
7-day runs: 12
30-day runs: 276
Model's Last Updated: August 04 2026
automatic-speech-recognition

Introduction of visualears-fastconformer-fa-full-ab

Model Details of visualears-fastconformer-fa-full-ab

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 ONNX FP fixed CTC core 100.00% CTC argmax parity
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 CoreML FP16 fixed CTC core 99.85% CTC argmax parity
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 CoreML 4-bit k-means palettized, quality-first variant 99.65% CTC argmax parity
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 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 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 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 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.

Runs of Reza2kn visualears-fastconformer-fa-full-ab on huggingface.co

354
Total runs
0
24-hour runs
0
3-day runs
12
7-day runs
276
30-day runs

More Information About visualears-fastconformer-fa-full-ab huggingface.co Model

More visualears-fastconformer-fa-full-ab license Visit here:

https://choosealicense.com/licenses/apache-2.0

visualears-fastconformer-fa-full-ab huggingface.co

visualears-fastconformer-fa-full-ab huggingface.co is an AI model on huggingface.co that provides visualears-fastconformer-fa-full-ab's model effect (), which can be used instantly with this Reza2kn visualears-fastconformer-fa-full-ab model. huggingface.co supports a free trial of the visualears-fastconformer-fa-full-ab model, and also provides paid use of the visualears-fastconformer-fa-full-ab. Support call visualears-fastconformer-fa-full-ab model through api, including Node.js, Python, http.

visualears-fastconformer-fa-full-ab huggingface.co Url

https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab

Reza2kn visualears-fastconformer-fa-full-ab online free

visualears-fastconformer-fa-full-ab huggingface.co is an online trial and call api platform, which integrates visualears-fastconformer-fa-full-ab's modeling effects, including api services, and provides a free online trial of visualears-fastconformer-fa-full-ab, you can try visualears-fastconformer-fa-full-ab online for free by clicking the link below.

Reza2kn visualears-fastconformer-fa-full-ab online free url in huggingface.co:

https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab

visualears-fastconformer-fa-full-ab install

visualears-fastconformer-fa-full-ab is an open source model from GitHub that offers a free installation service, and any user can find visualears-fastconformer-fa-full-ab on GitHub to install. At the same time, huggingface.co provides the effect of visualears-fastconformer-fa-full-ab install, users can directly use visualears-fastconformer-fa-full-ab installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

visualears-fastconformer-fa-full-ab install url in huggingface.co:

https://huggingface.co/Reza2kn/visualears-fastconformer-fa-full-ab

Url of visualears-fastconformer-fa-full-ab

visualears-fastconformer-fa-full-ab huggingface.co Url

Provider of visualears-fastconformer-fa-full-ab huggingface.co

Reza2kn
ORGANIZATIONS

Other API from Reza2kn

huggingface.co

Total runs: 936
Run Growth: 911
Growth Rate: 97.33%
Updated:July 26 2026
huggingface.co

Total runs: 312
Run Growth: 312
Growth Rate: 100.00%
Updated:August 10 2026
huggingface.co

Total runs: 255
Run Growth: 219
Growth Rate: 85.88%
Updated:September 24 2026
huggingface.co

Total runs: 87
Run Growth: 37
Growth Rate: 42.53%
Updated:September 10 2026
huggingface.co

Total runs: 52
Run Growth: 52
Growth Rate: 100.00%
Updated:August 13 2026
huggingface.co

Total runs: 6
Run Growth: -14
Growth Rate: -233.33%
Updated:October 10 2024
huggingface.co

Total runs: 0
Run Growth: 0
Growth Rate: 0.00%
Updated:September 26 2024