Downloads · 30 days
0
visualears-fastconformer-fa69m-onnx-fp16
Reza2kn/visualears-fastconformer-fa69m-onnx-fp16
visualears-fastconformer-fa69m-onnx-fp16 is a automatic speech recognition model from Reza2kn. Use it when you need speech turned into text. The card lists the license as apache-2.0.
Browser-ready ONNX export for the VisualEars 69M Persian ASR model.
Access
Public
Updated Jun 18, 2026
Repo size
282 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.onnx148 MB · 52%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Access
- Public
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026
- SHA
- 0fee91ca
Model card
From the Hugging Face model README
VisualEars FastConformer FA 69M ONNX FP16
Browser-ready ONNX export for the VisualEars 69M Persian ASR model.
- Weights: FP16
- Public IO: float32
processed_signal, int64processed_signal_length - Outputs: float32
logits, int64encoded_lengths - Fixed feature frames: 2005
- Vocab: BPE 1024 + CTC blank
Validation on the VisualEars worst-269 parity set:
- Exact transcript parity: 269/269 = 1.0
- Mean char similarity: 1.0
- Argmax step agreement: 0.9997360781208762
- ONNX nonempty rate: 267/269 = 0.9925650557620818
See export_manifest_fp16_iofp32.json and parity_full269_len_fp16_iofp32.json.
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Languages
- fa
- Created
- Jun 18, 2026
- Updated
- Jun 18, 2026