Upload ScribeFont FP32 safetensors + Int8 quantized ONNX + empirical report
Browse files- README.md +10 -10
- model.safetensors +1 -1
- onnx/model.onnx +1 -1
- onnx/model_quantized.onnx +2 -2
- training_summary.json +3 -3
README.md
CHANGED
|
@@ -39,7 +39,7 @@ Following the 3-tier scientific module playbook, `scribefont` separates **2D Con
|
|
| 39 |
| :--- | :--- | :---: | :---: | :--- |
|
| 40 |
| **Tier 1A: Neural Style-Conditioned (FP32)** | [`gnumanth/scribefont`](https://huggingface.co/gnumanth/scribefont) (`model.safetensors`) | `11.4 MB` | `2.94M` (`Conv2d` + `4-Layer Transformer`) | Few-shot unseen glyph synthesis from noisy camera scans, writer style extraction |
|
| 41 |
| **Tier 1B: Neural Quantized (Int8 ONNX)** | [`onnx/model_quantized.onnx`](https://huggingface.co/gnumanth/scribefont/tree/main/onnx) (`onnxruntime-web` WASM SIMD / CPU) | `3.15 MB` (`3.62x` smaller) | `2.94M` (`QUInt8` weights) | **100% Client-Side Browser WASM SIMD / WebGPU** handwriting-to-`.ttf` studio |
|
| 42 |
-
| **Tier 2: Zero-Dep Fast Engine** | `npm i scribefont` / `pip install scribefont` | `0.0 MB` (`~18 KB` code) | `0` (Deterministic Bézier + `.ttf` packer) | Ultra-low-latency (`0.
|
| 43 |
|
| 44 |
---
|
| 45 |
|
|
@@ -49,14 +49,14 @@ Evaluates synthesizing unseen target characters (`30` valid unseen glyphs + `30`
|
|
| 49 |
|
| 50 |
| Metric ($N=60$, $B=1,000$ Bootstrap 95% CI) | Tier 1A: PyTorch FP32 Neural | Tier 1B: ONNX Int8 Quantized (WASM/CPU) | Tier 2: Zero-Dep Geometric Engine |
|
| 51 |
| :--- | :---: | :---: | :---: |
|
| 52 |
-
| **Overall Accuracy (95% Bootstrap CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 53 |
-
| **Unseen-Glyph Style Fidelity (`MAE < 12 UPM`)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 54 |
-
| **Bézier Contour Coordinate MAE (`UPM`, lower is better)** | **2.
|
| 55 |
-
| **Advance-Width Prediction MAE (`UPM`)** | **
|
| 56 |
| **12-Writer Calligrapher Identification Accuracy** | **100.0%** | **100.0%** | 16.67% |
|
| 57 |
| **Blank/Smudge Cell Abstention (`p_missing > 0.5`)** | **100.0%** | **100.0%** | **100.0%** |
|
| 58 |
-
| **Abstention `p_missing` AUROC / 10-Bin ECE** | **1.0** / `0.
|
| 59 |
-
| **Latency `p50` / `p95` / `p99` (ms/glyph)** | `
|
| 60 |
|
| 61 |
---
|
| 62 |
|
|
@@ -67,10 +67,10 @@ Evaluates full-alphabet (`A-Z`, `a-z`, `0-9`) glyph contour synthesis, metric in
|
|
| 67 |
| Metric ($N=62$ alphanumeric glyphs) | Tier 1A: PyTorch FP32 Neural | Tier 1B: ONNX Int8 Quantized | Tier 2: Zero-Dep Fast Engine |
|
| 68 |
| :--- | :---: | :---: | :---: |
|
| 69 |
| **Glyph Fidelity Accuracy (95% Bootstrap CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 70 |
-
| **Bézier Contour MAE (`UPM`, out of `1000 UPM`)** | `
|
| 71 |
| **OpenType Metric Invariant (`adv >= w + lsb`)** | **100.0%** | **100.0%** | **100.0%** |
|
| 72 |
| **Compiled Binary `.ttf` Checksum & SFNT Validity** | **100.0%** (`7292 B`) | **100.0%** (`7292 B`) | **100.0%** (`7292 B`) |
|
| 73 |
-
| **Per-Glyph Latency `p50` / `p95` (ms)** | `
|
| 74 |
|
| 75 |
---
|
| 76 |
|
|
@@ -80,5 +80,5 @@ Evaluates full-alphabet (`A-Z`, `a-z`, `0-9`) glyph contour synthesis, metric in
|
|
| 80 |
| :--- | :---: | :---: | :---: |
|
| 81 |
| **Adversarial Glyph & Abstention Accuracy (95% CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 82 |
| **Calibrated `p_missing` AUROC** | **1.0** | **1.0** | **1.0** |
|
| 83 |
-
| **Abstention 10-Bin ECE / Brier Score** | `0.
|
| 84 |
|
|
|
|
| 39 |
| :--- | :--- | :---: | :---: | :--- |
|
| 40 |
| **Tier 1A: Neural Style-Conditioned (FP32)** | [`gnumanth/scribefont`](https://huggingface.co/gnumanth/scribefont) (`model.safetensors`) | `11.4 MB` | `2.94M` (`Conv2d` + `4-Layer Transformer`) | Few-shot unseen glyph synthesis from noisy camera scans, writer style extraction |
|
| 41 |
| **Tier 1B: Neural Quantized (Int8 ONNX)** | [`onnx/model_quantized.onnx`](https://huggingface.co/gnumanth/scribefont/tree/main/onnx) (`onnxruntime-web` WASM SIMD / CPU) | `3.15 MB` (`3.62x` smaller) | `2.94M` (`QUInt8` weights) | **100% Client-Side Browser WASM SIMD / WebGPU** handwriting-to-`.ttf` studio |
|
| 42 |
+
| **Tier 2: Zero-Dep Fast Engine** | `npm i scribefont` / `pip install scribefont` | `0.0 MB` (`~18 KB` code) | `0` (Deterministic Bézier + `.ttf` packer) | Ultra-low-latency (`0.0747 ms/glyph`) parametric glyph synthesis & binary `.ttf` compilation |
|
| 43 |
|
| 44 |
---
|
| 45 |
|
|
|
|
| 49 |
|
| 50 |
| Metric ($N=60$, $B=1,000$ Bootstrap 95% CI) | Tier 1A: PyTorch FP32 Neural | Tier 1B: ONNX Int8 Quantized (WASM/CPU) | Tier 2: Zero-Dep Geometric Engine |
|
| 51 |
| :--- | :---: | :---: | :---: |
|
| 52 |
+
| **Overall Accuracy (95% Bootstrap CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | 80.0% `[70.0, 90.0]` |
|
| 53 |
+
| **Unseen-Glyph Style Fidelity (`MAE < 12 UPM`)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | 60.0% `[40.0, 76.67]` |
|
| 54 |
+
| **Bézier Contour Coordinate MAE (`UPM`, lower is better)** | **2.38 UPM** | **2.39 UPM** | 11.13 UPM |
|
| 55 |
+
| **Advance-Width Prediction MAE (`UPM`)** | **13.93 UPM** | **14.02 UPM** | 35.5 UPM |
|
| 56 |
| **12-Writer Calligrapher Identification Accuracy** | **100.0%** | **100.0%** | 16.67% |
|
| 57 |
| **Blank/Smudge Cell Abstention (`p_missing > 0.5`)** | **100.0%** | **100.0%** | **100.0%** |
|
| 58 |
+
| **Abstention `p_missing` AUROC / 10-Bin ECE** | **1.0** / `0.00276` | **1.0** / `0.00282` | **1.0** / `0.0006` |
|
| 59 |
+
| **Latency `p50` / `p95` / `p99` (ms/glyph)** | `6.1797` / `8.3667` / `9.2688 ms` | `1.2708` / `1.5253` / `1.5695 ms` | **0.0539** / `0.0632` / `0.0716 ms` |
|
| 60 |
|
| 61 |
---
|
| 62 |
|
|
|
|
| 67 |
| Metric ($N=62$ alphanumeric glyphs) | Tier 1A: PyTorch FP32 Neural | Tier 1B: ONNX Int8 Quantized | Tier 2: Zero-Dep Fast Engine |
|
| 68 |
| :--- | :---: | :---: | :---: |
|
| 69 |
| **Glyph Fidelity Accuracy (95% Bootstrap CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 70 |
+
| **Bézier Contour MAE (`UPM`, out of `1000 UPM`)** | `0.98 UPM` | `0.98 UPM` | **0.0 UPM** |
|
| 71 |
| **OpenType Metric Invariant (`adv >= w + lsb`)** | **100.0%** | **100.0%** | **100.0%** |
|
| 72 |
| **Compiled Binary `.ttf` Checksum & SFNT Validity** | **100.0%** (`7292 B`) | **100.0%** (`7292 B`) | **100.0%** (`7292 B`) |
|
| 73 |
+
| **Per-Glyph Latency `p50` / `p95` (ms)** | `6.035` / `9.1311 ms` | `1.3858` / `1.9749 ms` | **0.0747** / `0.083 ms` |
|
| 74 |
|
| 75 |
---
|
| 76 |
|
|
|
|
| 80 |
| :--- | :---: | :---: | :---: |
|
| 81 |
| **Adversarial Glyph & Abstention Accuracy (95% CI)** | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` | **100.0%** `[100.0, 100.0]` |
|
| 82 |
| **Calibrated `p_missing` AUROC** | **1.0** | **1.0** | **1.0** |
|
| 83 |
+
| **Abstention 10-Bin ECE / Brier Score** | `0.00077` / `0.0` | `0.00077` / `0.0` | `0.0006` / `0.0` |
|
| 84 |
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11776632
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0a0f4b181cc6a5d940e9df2c2f676e7fe18e12f770055156a67f7a3721ca1e15
|
| 3 |
size 11776632
|
onnx/model.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 11954706
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d259cec17530d16f05b3598d8e788e28c54239ea6bbde09e7ad304a89ae08b12
|
| 3 |
size 11954706
|
onnx/model_quantized.onnx
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66d970169c7801fdc26ccf956cd93db6f70e979761a714373330afbd3b34c190
|
| 3 |
+
size 3307680
|
training_summary.json
CHANGED
|
@@ -2,11 +2,11 @@
|
|
| 2 |
"model": "ScribeFontForGeneration",
|
| 3 |
"parameters": 2941340,
|
| 4 |
"device": "mps",
|
| 5 |
-
"train_seconds":
|
| 6 |
"best_val_metrics": {
|
| 7 |
"missing_acc": 1.0,
|
| 8 |
"writer_acc": 1.0,
|
| 9 |
-
"contour_mae_upm": 1.
|
| 10 |
-
"advance_mae_upm": 2.
|
| 11 |
}
|
| 12 |
}
|
|
|
|
| 2 |
"model": "ScribeFontForGeneration",
|
| 3 |
"parameters": 2941340,
|
| 4 |
"device": "mps",
|
| 5 |
+
"train_seconds": 62.14,
|
| 6 |
"best_val_metrics": {
|
| 7 |
"missing_acc": 1.0,
|
| 8 |
"writer_acc": 1.0,
|
| 9 |
+
"contour_mae_upm": 1.25,
|
| 10 |
+
"advance_mae_upm": 2.77
|
| 11 |
}
|
| 12 |
}
|