Whisper Chileno

Whisper Chileno

Turns Chilean Spanish speech into text, tuned for call center audio with a LoRA adapter on Whisper large-v3. A demo for speech teams and call center developers.

Made by hablaip 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: Whisper Chileno is a demo that transcribes Chilean Spanish speech, with call center audio as its target. It pairs the whisper-large-v3 model from OpenAI with a LoRA adapter tuned to that domain.

The README credits HablaIP SpA and a CORFO project. The example audio in the Space is synthetic, made with text to speech, and holds no real customer data.

Who it suits: Teams that need to turn spoken Chilean Spanish into text, and people who want to hear how a domain adapter changes a base speech model.

Industry | Who uses it | How they use it | Example
Customer service | Call center teams | Turn recorded calls into text for review | Run a sample call and read the transcript
Speech research | Machine learning engineers | Compare the adapter with the base model | Try the same clip on both models
Language technology | Spanish speech developers | Test recognition of Chilean speech | Play one of the included samples

You can skip it if your audio is in another language or you need a finished transcription service.

Where to use it:

• A web browser, on the Space's page at Hugging Face, with nothing to install
• Windows, macOS or Linux with Python, from a copy you download

Use case | Who | What they get back
Transcribe a call | Call center teams | The spoken Chilean Spanish as text
Try the demo audio | Developers | A transcript of a synthetic sample clip
Check the adapter | Researchers | Output from the domain-tuned model

How to set it up:

• Python on your computer
• The Python packages listed in requirements.txt
• The huggingface_hub package, which gives you the hf command

1. Install the huggingface_hub package.
2. Download the Space with the hf command.
3. Move into the downloaded folder.
4. Install the pinned Gradio version.
5. Install the packages from requirements.txt.
6. Start the app with Python.

pip install -U huggingface_hub
hf download hablaip/whisper-chileno-demo --repo-type space --local-dir whisper-chileno-demo
cd whisper-chileno-demo
pip install gradio==6.22.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space's page in your browser, or start your own copy with the command below. Then load one of the example audio files from the samples folder and read the text the demo returns.

python app.py

Example: You load one of the synthetic sample calls into the demo. It returns the Chilean Spanish speech in that clip as written text, which you can compare with what you hear.

For newcomers and experts: If you are new to speech recognition, open the page and run one sample clip. Listen to it, then read the transcript to see how close the two are.

If you know the field, the setup is a base Whisper model plus a LoRA adapter. An adapter changes a small set of weights instead of retraining the whole model, which keeps the tuned part small. The Space runs on basic CPU hardware at Hugging Face.

You load a sample audio clip
app.py passes it to whisper-large-v3
The LoRA adapter tunes it to call center speech
The transcript shows on the page

Good to know:

• License: the Space lists apache-2
• Cost to run: none named
• Data it reaches: the audio you give it, plus the files in the Space
• Not for: real customer data, since the included samples are synthetic and the README calls this a demo

On Hugging Face, 13 November 2026

• Likes: 1
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/hablaip/whisper-chileno-demo
• Files: https://huggingface.co/spaces/hablaip/whisper-chileno-demo/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.