diff options
Diffstat (limited to 'README.md')
| -rw-r--r-- | README.md | 12 |
1 files changed, 7 insertions, 5 deletions
@@ -18,8 +18,9 @@ server, no account, no sign-up and no tracking code in the app. `Clean → Validate`, `Translate Only`, `Clean Only`. - **Translate into 16 target languages** offered in the page: English, Spanish, French, German, Italian, Portuguese, Chinese, Japanese, Korean, Russian, Arabic, Hindi, - Turkish, Dutch, Polish, Swedish. Text is split into 1,500-character chunks and sent - one chunk at a time, with pause and stop buttons and a token counter. + Turkish, Dutch, Polish, Swedish. The text is split at word boundaries and sent one + chunk at a time (1,500 characters by default, 2,500 when a `:cloud` model is chosen), + with pause and stop buttons and a token counter. - **Settings tab** — API source (Proxied `/ollama`, Local `localhost:11434`, or a Custom URL), optional API key, *Refresh Models* (reads `/api/tags`), and chunk size. @@ -42,9 +43,10 @@ pdf2txt/ ## How to run it -The page loads PDF.js as a Web Worker, and browsers refuse to start a worker from a -`file://` URL. So double-clicking `src/index.html` will load but extraction will fail. -Serve the folder over plain HTTP instead — no dependencies, Python 3 is enough: +The page loads PDF.js as a Web Worker. Some browsers refuse to start a worker from a +`file://` URL (Chrome blocks it; a headless Chromium on this host happened to allow it), +so double-clicking `src/index.html` may load but extract nothing. If that happens, serve +the folder over plain HTTP — no dependencies, Python 3 is enough: ```bash cd products/pdf2txt |