Dialogatexto

Dialogatexto

Answers Spanish questions from a text using two named Spanish question answering models in a Streamlit page. For Spanish speakers, students and developers trying document Q&A.

Made by jcmachicao on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Dialogatexto is a Streamlit app for asking questions about a text in Spanish. The record names two Spanish BERT models fine-tuned for question answering. Two text files sit in the repository, one named for a data science course and one for trout in Peru.

Who it suits: It suits Spanish speakers who want answers pulled from a passage, students of question answering, and developers who want a small Streamlit example. The two text files look like sample material, but the record does not say so.

Industry | Who uses it | How they use it | Example
Education | Spanish-speaking students | Ask questions about a study text | Ask what a course text says on one topic
Research | NLP students | Try Spanish question answering models | Compare answers from the two models
Software | Python developers | Read a small question answering app | Open app.py and follow how a text is passed in

You can skip it if your texts are not in Spanish.

Where to use it:

• A web browser, on the Space's page on Hugging Face
• Windows, macOS or Linux with Python, from a downloaded copy

Use case | Who | What they get back
Ask a question about a text | Readers and students | An answer found in the passage
Compare two models | Researchers | Answers from a full and a distilled Spanish model
Reuse as a base | Developers | A small Streamlit app to adapt

How to set it up:

• Nothing at all if you use the online Space
• Python on your computer, only if you run a copy
• The packages listed in requirements.txt

1. Open the Space's page in a browser to use it with nothing to install.
2. To run a copy, install the Hugging Face Hub package and download the Space.
3. Move into the new folder, then install Streamlit and the listed requirements.
4. Start the app with Streamlit.

pip install -U huggingface_hub
hf download jcmachicao/dialogatexto --repo-type space --local-dir dialogatexto
cd dialogatexto
pip install streamlit
pip install -r requirements.txt
streamlit run app.py

How to use it: Online, open the Space and use the controls on its page. On your own machine, run the main file with Streamlit from the Space folder, then use the page it serves. The record does not list the controls, so look at the page.

streamlit run app.py

Example: You open the Space, choose or paste a Spanish text and type a question about it in Spanish. The app returns the answer the model finds in that text. The record shows no sample, so the exact controls depend on the page.

For newcomers and experts: Question answering means a model reads a text and picks out the part that answers your question. Start by opening the Space and asking a simple question about a short Spanish passage.

If you know the field, both named models are fine-tuned on a Spanish version of the SQuAD 2 task, and one of them is a distilled version. SQuAD 2 style models can also decide a text has no answer. The record gives no accuracy figures.

You pick a text and ask a question
The app passes both to a Spanish model
The model finds the answer in the text
The page shows the answer

Good to know:

• License: cc-by-sa-4, as listed on the Space
• Cost to run: none named
• Data it reaches: the text and question you give it, the two named models and the text files in the repository
• Not for: the record names no exclusions, and it covers Spanish text

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: streamlit
• License: cc-by-sa-4.0

Links

• Space: https://huggingface.co/spaces/jcmachicao/dialogatexto
• Files: https://huggingface.co/spaces/jcmachicao/dialogatexto/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.