Spaces:
Sleeping
Sleeping
| title: Markdown To CSV Converter (for Threadscope) | |
| emoji: 🏢 | |
| colorFrom: green | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: 6.3.0 | |
| app_file: app.py | |
| pinned: false | |
| license: mit | |
| short_description: 'Turn .md / .txt into csv ' | |
| ## What this tool does | |
| This tool converts structured chat transcripts written in Markdown or plain text | |
| into a canonical turn-level CSV format suitable for analysis with **Threadscope: | |
| Drift & Hold**. | |
| ## Supported transcript format | |
| This converter expects transcripts that use explicit speaker markers, for example: | |
| - 'You said: Hello' | |
| - 'ChatGPT said: Hi there' | |
| Marker strings are configurable in the UI, but the transcript must follow a | |
| consistent “marker → content” pattern. | |
| ## Not supported | |
| - Arbitrarily formatted prose | |
| - Chat logs without explicit speaker markers | |
| - Exported HTML or JSON without preprocessing | |
| ## Output | |
| The generated CSV includes the following columns: | |
| - `turn` | |
| - `speaker` | |
| - `chars` | |
| - `words` | |
| - `tokens_est` (lightweight estimate) | |
| ## How this fits into the Threadbourne lab | |
| This tool is intended as a preprocessing step for use with | |
| **Threadscope: Drift & Hold**, which visualizes long-form interaction dynamics | |
| such as drift, stability, and perturbation response. | |
| ## Privacy | |
| Files are processed in-session only and are not stored. | |
| Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference | |