Downloads · 30 days
25
30% of all-time downloads
visualears-fastconformer-fa-full-ab-nvfp4
Reza2kn/visualears-fastconformer-fa-full-ab-nvfp4
visualears-fastconformer-fa-full-ab-nvfp4 is a automatic speech recognition model from Reza2kn. Use it when you need speech turned into text. It is set up for nemo. The card lists the license as apache-2.0.
NVFP4 (W4A4) post-training quantization of Reza2kn/visualears-fastconformer-fa-full-ab via NVIDIA modelopt.
All-time downloads
84
Public
Repo size
459 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.nemo459 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026
- SHA
- deb386f1
Base models
Datasets
Model card
From the Hugging Face model README
visualears-fastconformer-fa-full-ab-nvfp4
NVFP4 (W4A4) post-training quantization of Reza2kn/visualears-fastconformer-fa-full-ab via NVIDIA modelopt.
- Base architecture: EncDecHybridRNNTCTCBPEModel (NeMo)
- Calibration: 32 Persian clips from
Reza2kn/persian-asr-eval-v0(held out from eval). - Hardware target: NVIDIA Blackwell tensor cores.
Eval — Reza2kn/persian-asr-eval-v0 (FLEURS-fa, 200 clips)
| Variant | WER ↓ | CER ↓ | per-clip latency | peak VRAM |
|---|---|---|---|---|
| NVFP4 (this repo) | 20.33% | 7.38% | 48 ms | 603 MiB |
Usage
import nemo.collections.asr as nemo_asr
m = nemo_asr.models.ASRModel.restore_from("visualears-fastconformer-fa-full-ab-NVFP4.nemo").cuda().eval()
transcripts = m.transcribe(["clip.wav"])
print(transcripts[0])
License
Inherits the base model's license.
- Task
- Automatic Speech Recognition
- Library
- nemo
- License
- apache-2.0
- Languages
- fa
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026