Downloads · 30 days
0
visualears-fastconformer-fa-full-ab-onnx-w2-progressive
Reza2kn/visualears-fastconformer-fa-full-ab-onnx-w2-progressive
visualears-fastconformer-fa-full-ab-onnx-w2-progressive 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.
Fixed-frame ONNX CTC acoustic core exported from the progressive 2-bit QAT materialized checkpoint:
Access
Public
Updated Jun 12, 2026
Repo size
469 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.data458 MB · 98%
At a glance
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Access
- Public
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026
- SHA
- b1c4d505
Base models
Model card
From the Hugging Face model README
VisualEars FastConformer FA W2 Progressive ONNX
Fixed-frame ONNX CTC acoustic core exported from the progressive 2-bit QAT materialized checkpoint:
onebit_progressive_l0_fast_no_urls_lower3_20260612_170013/fa_fastconformer_qat_w2_cotrained_materialized.nemo
This is the same browser-facing interface as the FP demo:
- input:
processed_signal, float32[batch, 80, 2005] - outputs:
logits[batch, 251, 1025],encoded_lengths[batch] - external data:
fastconformer_ctc_fixed2005.onnx.data
Important: this ONNX is exported from a materialized QAT checkpoint. The selected weights are projected to W2 values, but this is not bit-packed/compressed yet.
VisualEars269 score for the source W2 materialized checkpoint:
| decode | WER | CER |
|---|---|---|
| default | 36.92% | 17.07% |
| forced CTC | 39.67% | 17.86% |
- Task
- Automatic Speech Recognition
- License
- apache-2.0
- Languages
- fa
- Created
- Jun 12, 2026
- Updated
- Jun 12, 2026