Downloads · 30 days
0
0% of all-time downloads
visualears-fastconformer-fa-full-ab-coreml-w4
Reza2kn/visualears-fastconformer-fa-full-ab-coreml-w4
visualears-fastconformer-fa-full-ab-coreml-w4 is a automatic speech recognition model from Reza2kn. Use it when you need speech turned into text. It is set up for coreml. The card lists the license as apache-2.0.
Derivative export of Reza2kn/visualears-fastconformer-fa-full-ab.
All-time downloads
12
Public
Repo size
110 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin109 MB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- coreml
- License
- apache-2.0
- Access
- Public
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026
- SHA
- a1e9db66
Base models
Model card
From the Hugging Face model README
VisualEars FastConformer Persian ASR CoreML W4
Derivative export of Reza2kn/visualears-fastconformer-fa-full-ab.
Artifact
- Format: CoreML 4-bit k-means palettized export
- Quantization/conversion: CoreML palettize_weights, k-means, nbits=4, weight_threshold=1000000
- Runtime validation: CoreML CPU
- Validation result: 98.06% CTC argmax parity
- Size: 110 MB, 50.2% of CoreML FP16 source
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
Best compressed verified CoreML 4-bit package. Full CoreML W4 k-means failed at 90.11% parity.
- Task
- Automatic Speech Recognition
- Library
- coreml
- License
- apache-2.0
- Languages
- fa
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026