|
|
--- |
|
|
title: Sindhi Speech-to-Text |
|
|
emoji: 🎙️ |
|
|
colorFrom: pink |
|
|
colorTo: purple |
|
|
sdk: gradio |
|
|
sdk_version: "4.29.0" |
|
|
app_file: app.py |
|
|
pinned: false |
|
|
license: apache-2.0 |
|
|
--- |
|
|
|
|
|
# Sindhi Speech-to-Text (Whisper) |
|
|
|
|
|
This Hugging Face Space uses the **steja/whisper-large-sindhi** model to transcribe Sindhi speech into text. |
|
|
You can upload or record Sindhi audio and get accurate text output. |
|
|
|
|
|
## 🚀 Usage |
|
|
- Click "Upload" to provide a Sindhi audio file, or use "Microphone" to record live speech. |
|
|
- The app will return a transcription in Sindhi text. |
|
|
|
|
|
## ⚙️ Model |
|
|
- Model: [steja/whisper-large-sindhi](https://huggingface.co/steja/whisper-large-sindhi) |
|
|
- Framework: Hugging Face Transformers + Gradio |
|
|
- License: Apache-2.0 |
|
|
|
|
|
## 📌 Notes |
|
|
- Large model may run slowly on CPU Spaces. |
|
|
- If GPU not available, switch to `steja/whisper-small-sindhi` in `app.py`. |
|
|
|
