summaryrefslogtreecommitdiff
path: root/README.md
diff options
context:
space:
mode:
Diffstat (limited to 'README.md')
-rw-r--r--README.md12
1 files changed, 7 insertions, 5 deletions
diff --git a/README.md b/README.md
index 566b335..a55d2ed 100644
--- a/README.md
+++ b/README.md
@@ -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