Persian ASR

Persian ASR

Turns spoken Persian into text with a wav2vec2 speech model in a Gradio page. For students, developers and anyone who needs a transcript of Persian audio.

Made by SajjadAyoubi 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 from SajjadAyoubi does automatic speech recognition for Persian, which means turning speech into written text. It names one model, masoudmzb/wav2vec2-xlsr-multilingual-53-fa, and the repository also holds a file named kenlm.scorer. You use it in a browser, or you run a copy on your own computer.

Who it suits: It suits people who need a transcript of Persian audio, and students and developers who want to see a speech model at work.

Industry | Who uses it | How they use it | Example
Media | Journalists | Get a rough text of a Persian interview | Upload a short recording and read the text
Education | Language students | Check how a speech model hears Persian | Speak a sentence and compare it to the output
Software | Python developers | Read how a wav2vec2 model is served in Gradio | Download the Space and open app.py

Skip it if you need other languages or a finished transcript, because the model is for Persian and its output needs a check.

Where to use it:

• A web browser: go to the Space on Hugging Face and try it with no install
• Windows, macOS or Linux: run a copy with Python

Use case | Who | What they get back
Transcribe a clip | Journalists | Persian text for a short recording
Test the model | Students | A quick look at how it hears different voices
Study the code | Developers | An app.py that loads a speech model and a scorer file

How to set it up: You need a few things in place first.

• Python with pip, on Windows, macOS or Linux
• An internet connection to fetch the files from Hugging Face
• Spare disk space, since the speech model may need a large download on the first run

1. Install the Hugging Face hub package.
2. Download the Space into a local folder.
3. Move into that folder.
4. Install Gradio and the packages listed in requirements.txt.
5. Start the app.

pip install -U huggingface_hub
hf download SajjadAyoubi/Persian-ASR --repo-type space --local-dir Persian-ASR
cd Persian-ASR
pip install gradio
pip install -r requirements.txt
python app.py

How to use it: Online, use the Gradio interface the Space page shows. On your own computer, run the main file from the project folder and open the page it serves in your browser.

python app.py

Example: You run python app.py inside the project folder, open the page and give it a short recording of someone speaking Persian. The page returns the text the model heard.

For newcomers and experts: If this is new to you, start online. Go to the Space and try a short clip before you install anything. Speech recognition means the program writes down what it hears.

If you know the field, note that the named model is a multilingual wav2vec2 XLSR model with a fa suffix, and that a kenlm.scorer file sits beside app.py. The source gives no error rates, so test it on your own audio.

Open the Space or run app.py
The Gradio page loads
You give it Persian audio
The wav2vec2 model reads it
The text appears on the page

Good to know: Speech models can mishear names and noisy audio, so check the transcript against the recording.

• License: mit
• Cost to run: none named, no API key, account or paid service
• Data it reaches: the audio you give it and the model it names, with nothing else listed

On Hugging Face, 13 November 2026

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

Links

• Space: https://huggingface.co/spaces/SajjadAyoubi/Persian-ASR
• Files: https://huggingface.co/spaces/SajjadAyoubi/Persian-ASR/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.