docs: add code-tape model card

README.md

@@ -0,0 +1,156 @@
+---
+license: apache-2.0
+base_model: ceilf6/code-tape-subtitle-postprocessor-merged
+library_name: transformers.js
+pipeline_tag: text-generation
+language:
+- zh
+- en
+tags:
+- onnx
+- transformers.js
+- webgpu
+- wasm
+- code-tape
+- subtitle-correction
+- chapter-generation
+---
+
+# code-tape subtitle postprocessor ONNX
+
+This is the browser-local ONNX export of the code-tape subtitle post-processing model. It is the default LLM used by the code-tape web app for the "纠错并生成章节" workflow.
+
+The model receives ASR subtitle segments plus code context and returns strict JSON:
+
+- sparse subtitle corrections for frontend/code terminology;
+- playback chapter jump points derived from subtitle timestamps;
+- no Markdown, no explanation, no extra wrapper text.
+
+This model is not ASR. In code-tape, ASR is handled separately by Whisper; this ONNX model only post-processes the resulting subtitle text.
+
+## Repository role
+
+code-tape publishes this model family in three forms:
+
+| Repository | Purpose |
+| --- | --- |
+| [`ceilf6/code-tape-subtitle-postprocessor-lora`](https://huggingface.co/ceilf6/code-tape-subtitle-postprocessor-lora) | LoRA adapter for reproducibility and continued fine-tuning. |
+| [`ceilf6/code-tape-subtitle-postprocessor-merged`](https://huggingface.co/ceilf6/code-tape-subtitle-postprocessor-merged) | Full merged Hugging Face model. |
+| [`ceilf6/code-tape-subtitle-postprocessor-onnx`](https://huggingface.co/ceilf6/code-tape-subtitle-postprocessor-onnx) | This Transformers.js-compatible ONNX export for browser-local inference. |
+
+Use this repository when integrating with the browser app.
+
+## Intended contract
+
+Input payload:
+
+```json
+{
+  "context": {
+    "fileName": "SubtitlePanel.tsx",
+    "code": "await postProcessor.process({ track, context });",
+    "runtimeOutput": "",
+    "glossary": ["SubtitlePanel", "postProcessor", "chapters"]
+  },
+  "segments": [
+    { "id": "subtitle-1", "startMs": 0, "endMs": 1600, "text": "这里创建 hugging face 字幕 post processor" },
+    { "id": "subtitle-2", "startMs": 1600, "endMs": 3300, "text": "最后生成 corrections 和 chapters" }
+  ]
+}
+```
+
+Expected output shape:
+
+```json
+{
+  "segments": [
+    { "id": "subtitle-1", "text": "这里创建 Hugging Face 字幕 postProcessor" }
+  ],
+  "chapters": [
+    { "title": "创建字幕后处理器", "startMs": 0, "endMs": 1600 },
+    { "title": "生成纠错和章节", "startMs": 1600, "endMs": 3300 }
+  ]
+}
+```
+
+`segments` is a sparse change set. Omitted subtitle segments are treated as unchanged by the application.
+
+## Browser usage
+
+```javascript
+import { pipeline } from "@huggingface/transformers";
+
+const generator = await pipeline(
+  "text-generation",
+  "ceilf6/code-tape-subtitle-postprocessor-onnx",
+  { device: "webgpu", dtype: "q4f16" },
+);
+
+const messages = [
+  {
+    role: "system",
+    content: [
+      "You are the code-tape subtitle post-processing model.",
+      "Only output one JSON object.",
+      "Goal: correct ASR subtitle text for frontend/code terms and create playback chapter jump points.",
+      'Output shape: {"segments":[{"id":"subtitle-1","text":"corrected text"}],"chapters":[{"title":"问题分析","startMs":0,"endMs":1000}]}',
+    ].join("\n"),
+  },
+  {
+    role: "user",
+    content: JSON.stringify({
+      context: { fileName: "Counter.tsx", code: "", runtimeOutput: "", glossary: ["useState"] },
+      segments: [{ id: "subtitle-1", startMs: 0, endMs: 1200, text: "这里用 use state" }],
+    }),
+  },
+];
+
+const output = await generator(messages, {
+  max_new_tokens: 384,
+  do_sample: false,
+  return_full_text: false,
+});
+```
+
+In production, code-tape tries WebGPU first and falls back to WASM/CPU-compatible settings when needed. The application also handles browser cache write failures and validates every model response before applying it.
+
+## Integration notes
+
+- Public browser loading does not require a Hugging Face token.
+- Keep prompts short. The code-tape app budgets source code, runtime output, and output token count to keep local inference responsive.
+- Validate JSON before use. Invalid JSON, unknown segment ids, duplicate ids, empty text, overlapping chapters, or chapters outside the subtitle timeline must fall back safely.
+- This model should run after ASR, not before ASR.
+
+## Training and export lineage
+
+1. Fine-tune a LoRA adapter from `HuggingFaceTB/SmolLM2-135M-Instruct`.
+2. Merge the adapter into a full Hugging Face model.
+3. Export/quantize the merged model to ONNX for `@huggingface/transformers` browser inference.
+
+## Evaluation
+
+code-tape evaluates this model family with project-specific checks:
+
+- JSON parseability;
+- sparse segment reference validity;
+- glossary preservation after sparse corrections are applied to the source subtitles;
+- chapter ordering, overlap, and bounds within the subtitle timeline.
+
+No broad general-purpose benchmark score is claimed.
+
+## Limitations
+
+- The model is small and domain-specific; malformed JSON is possible.
+- It is optimized for frontend/code explanation subtitles, not arbitrary subtitles.
+- It cannot transcribe audio.
+- Long subtitle tracks should be split before local browser inference.
+
+## Privacy and security
+
+The intended path is browser-local inference. Audio transcription, subtitle correction, and chapter generation can run without sending media or subtitles to a hosted inference API.
+
+Do not include secrets, private source code, credentials, or access tokens in prompts unless you control the full runtime and storage environment.
+
+## License
+
+Apache-2.0, following the base model license.