Spaces:
Running
Running
Download progress.html from thanujhf/akshara-ocr-studio: direct link, hf CLI and curl.
- Browser
- Download file 3.92 kB
-
https://huggingface.co/spaces/thanujhf/akshara-ocr-studio/resolve/main/progress.html
- Command line
-
hf download hf://spaces/thanujhf/akshara-ocr-studio/progress.html
-
curl -L -o progress.html https://huggingface.co/spaces/thanujhf/akshara-ocr-studio/resolve/main/progress.html
3.92 kB
| <html lang="en"><meta charset="utf-8"><meta name="viewport" content="width=device-width,initial-scale=1"><link rel="icon" href="favicon.svg" type="image/svg+xml"><title>Akshara · Study progress</title> | |
| <style>body{margin:0;background:#f5f3fb;color:#252139;font:16px/1.6 system-ui}main{max-width:1060px;margin:32px auto;padding:24px}h1{font-size:40px;line-height:1.2}a{color:#6943b4}article{background:#fff;border:1px solid #e6e0f0;border-radius:18px;padding:24px;margin:18px 0}.grid{display:grid;grid-template-columns:repeat(3,1fr);gap:16px}.grid article{margin:0}.muted,small{color:#696477}strong.value{display:block;font-size:30px}progress{width:100%;height:18px}pre{white-space:pre-wrap;overflow-wrap:anywhere;font-size:13px}table{width:100%;border-collapse:collapse}td,th{text-align:left;padding:10px;border-bottom:1px solid #eee}.tag{font-weight:700;color:#6b45c5}@media(max-width:700px){.grid{grid-template-columns:1fr}h1{font-size:30px}main{padding:16px}}</style> | |
| <main><span class="tag">AKSHARA / TEMPORARY STUDY DASHBOARD</span><h1>Training and testing progress</h1><p><a href="/">OCR studio</a> · <a href="/research-v2">Research details</a> ? <a href="analysis.html">Final analysis & benchmarks</a></p><p class="muted">Windows RTX 3050 · One capped training epoch · Validation selects the model · Final test stays sealed until selection.</p> | |
| <article aria-live="polite"><small id="state">Connecting</small><h2 id="stage">Reading measured run state</h2><progress id="bar" max="100" value="0" aria-label="Current stage progress"></progress><p id="progress">Waiting for a progress record.</p><p id="timing" class="muted"></p><small id="updated"></small></article> | |
| <div class="grid"><article><small>Frozen training examples</small><strong class="value" id="train">Pending</strong></article><article><small>Frozen validation examples</small><strong class="value" id="validation">Pending</strong></article><article><small>Sealed final-test examples</small><strong class="value" id="final-test">Pending</strong></article></div> | |
| <article><h2>Measured validation results</h2><table><thead><tr><th>Model</th><th>Examples</th><th>CER</th><th>Exact word</th></tr></thead><tbody id="metrics"></tbody></table><p class="muted">No candidate improvement is claimed before a supported validation comparison.</p></article> | |
| <article><h2>Independent final word-crop results</h2><p id="finalStatus">Sealed; no final results are available.</p><div id="finalResults" hidden><div style="overflow-x:auto" tabindex="0" aria-label="Final results table"><table><thead><tr><th>Model</th><th>Examples</th><th>Raw CER</th><th>NFC CER</th><th>Raw WER</th><th>NFC WER</th><th>Raw exact</th><th>NFC exact</th></tr></thead><tbody id="finalMetrics"></tbody></table></div><p id="pairedIntervals" class="muted"></p><details><summary>Output diagnostics, latency, memory and subgroups</summary><pre id="finalDiagnostics"></pre></details><p class="muted">These results cannot change validation-locked selection. Intervals are paired by source-document and duplicate components; verified writer identities are unavailable. API parity remains a separate requirement.</p></div></article> | |
| <article><h2>Model handoff</h2><p id="selection">Selection has not been locked.</p><p id="api">Checking API availability.</p><p class="muted">Inference pauses during GPU work. Training completion alone does not prove API parity. Final results describe word crops; writer identity, pretraining overlap and complete human label verification remain unknown.</p></article> | |
| <article><h2>Failure and recovery</h2><pre id="failure">No reported coordinator failure.</pre><p class="muted">Checkpoints are versioned and checksum verified. Smoke and benchmark weights are separate from the full training run.</p></article></main> | |
| <script src="deployment-config.js?v=20261016.1"></script><script src="progress.js?v=20261015.2"></script></html> | |