README.md

metadata

title: Whisper ASR API
emoji: 🎙️
colorFrom: blue
colorTo: green
sdk: gradio
sdk_version: 4.44.0
app_file: app.py
pinned: false

Whisper ASR - Speech Recognition API

This Space provides automatic speech recognition using OpenAI's Whisper model.

Features

• Multi-language support (99+ languages)
• Upload audio files or record directly
• Fast transcription using Whisper Base model
• Automatic language detection

API Usage

You can call this Space programmatically:

from gradio_client import Client

client = Client("YOUR_USERNAME/whisper-asr-api")
result = client.predict(
    audio="path/to/audio.wav",
    api_name="/predict"
)
print(result)

Model

• Using: Whisper Base
• Size: ~140 MB
• Performance: Fast with good accuracy