Downloads · 30 days
0
0% of all-time downloads
visualears-fastconformer-fa-full-ab-coreml-fp16
Reza2kn/visualears-fastconformer-fa-full-ab-coreml-fp16
visualears-fastconformer-fa-full-ab-coreml-fp16 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
16
Public
Repo size
219 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.bin218 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
- cadc810c
Base models
Model card
From the Hugging Face model README
VisualEars FastConformer Persian ASR CoreML FP16
Derivative export of 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.
- Task
- Automatic Speech Recognition
- Library
- coreml
- License
- apache-2.0
- Languages
- fa
- Created
- Jun 11, 2026
- Updated
- Jun 11, 2026