Merge remote-tracking branch 'refs/remotes/origin/main'

.gitignore

@@ -1,3 +1 @@
-translator_app/.venv
-translator_app
-translator_app/db.sqlite3
+translator_app/.venv

README.md

@@ -1,11 +1,33 @@
----
-title: Translator Model Api
-emoji: 📊
-colorFrom: indigo
-colorTo: green
-sdk: docker
-pinned: false
-short_description: Holds and serves lightweight translation models
----
-
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# The Translator App
+
+## Run locally
+
+```bash
+cd translator_app
+python -m venv .venv
+source .venv/bin/activate  # Windows: .venv\Scripts\activate
+pip install -r ../requirements.txt
+python manage.py migrate
+python manage.py runserver
+```
+
+Open http://127.0.0.1:8000/. The translation page has an API-backed submit
+flow, language selectors, model picker, and persisted history at `/history/`.
+
+## Configure a provider
+
+Create `translator_app/.env` with a Hugging Face token before translating:
+
+```env
+HF_TOKEN=hf_your_access_token
+TRANSLATION_DEFAULT_MODEL=nllb_600m
+```
+
+The primary model picker is configured for NLLB-200 600M, NLLB-200 1.3B, and
+MADLAD-400 3B through Hugging Face Inference Providers. NLLB language codes
+are mapped in the service before a request is sent. The selected model is sent
+by the UI and saved with each history item.
+
+For an optional DeepL-compatible fallback, additionally set
+`TRANSLATION_API_KEY` (and optionally `TRANSLATION_API_URL`). It will appear in
+the model picker only when configured.

requirements.txt

@@ -2,4 +2,4 @@ Django>=5.2
 djangorestframework>=3.15
 python-dotenv>=1.0
 requests>=2.31
-langdetect>=1.0.9
+langdetect>=1.0.9