---
title: Whisper Speech Transcription
emoji: 🎙️
colorFrom: blue
colorTo: purple
sdk: gradio
sdk_version: 5.41.1
app_file: app.py
pinned: false
license: mit
short_description: use finetuned s2t model
---

# Whisper Speech Transcription

AI-powered speech-to-text with timestamps using fine-tuned Whisper model.

## Features
- Upload audio files (up to 3 minutes)
- Record voice directly
- Get timestamped transcriptions
- Download JSON and SRT formats
- Optimized for English speech

## Usage
1. Choose upload or record option
2. Process your audio (max 3 minutes)
3. View transcription with timestamps
4. Download results in multiple formats


Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference