TFM_SimilitudSemantica_Fichero

TFM_SimilitudSemantica_Fichero

Compares how close in meaning texts are, using a multilingual BERT model in a Gradio page, with a sample JSON file included. For NLP students and researchers.

Made by jfarray 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: This Gradio app, going by its Spanish name, measures semantic similarity, meaning how close in meaning texts are, and takes its input from a file. The one model named is a multilingual BERT model. The repository includes TestFile.json, which looks like sample input.

Who it suits: It suits NLP students and researchers who want to try a multilingual model on text similarity, and developers who want a small example that reads a file. The record has no usage notes, so the page itself is the guide.

Industry | Who uses it | How they use it | Example
Research | NLP researchers | Check how close in meaning two texts are | Run the sample file and read the scores
Education | Language students | See how a model judges similar sentences | Compare a sentence with a reworded one
Software | Python developers | Read a small app that loads input from a file | Open app.py next to TestFile.json

You can skip it if you need a single-sentence chat tool, since it is built around file input.

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
Score text similarity | Researchers | A similarity result for the texts in a file
Try a multilingual model | Students | A view of how one BERT model handles meaning
Reuse as a base | Developers | A small Gradio app that reads a file

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 Gradio and the listed requirements.
4. Start the app with Python.

pip install -U huggingface_hub
hf download jfarray/TFM_SimilitudSemantica_Fichero --repo-type space --local-dir TFM_SimilitudSemantica_Fichero
cd TFM_SimilitudSemantica_Fichero
pip install gradio
pip install -r requirements.txt
python 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 from the Space folder, then use the page it serves. TestFile.json is the quickest sample to try, if the page asks for a file.

python app.py

Example: You open the Space and give it a file such as TestFile.json. The app returns a similarity result for the texts inside. The record does not describe the file format or the output, so check the page and the file.

For newcomers and experts: Semantic similarity asks whether two pieces of text mean the same thing, even when the words differ. Start by opening the Space and trying the sample file.

If you know the field, the app builds on a multilingual uncased BERT model, so it can handle several languages. The record gives no scoring method, thresholds or accuracy figures, so read app.py to see what it computes.

You give the page an input file
The app reads the texts in it
The BERT model turns each text into a vector
The app compares them and shows the result

Good to know:

• License: Unlicense, as listed on the Space
• Cost to run: none named
• Data it reaches: the file you give it and the model it names
• Not for: the record names no exclusions, and it gives no accuracy figures

On Hugging Face, 13 November 2026

• Likes: 0
• Built with: gradio
• License: unlicense

Links

• Space: https://huggingface.co/spaces/jfarray/TFM_SimilitudSemantica_Fichero
• Files: https://huggingface.co/spaces/jfarray/TFM_SimilitudSemantica_Fichero/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.