Whisper Large V3 Turbo

High-performance speech recognition and transcription model

Model Details

Advanced speech recognition model with great accuracy, speed, and multilingual support. Optimized for real-time transcription with enhanced performance on diverse audio conditions, accents, and terminology.

Parameters

809 million

Context Window

30 seconds of audio

Recommended Use

Ideal for transcription services, captioning, voice interfaces, and multilingual audio processing applications.

Supported Languages

Supports 90+ languages with high accuracy across diverse accents and dialects

Usage Examples

Installation:

pip install tinfoil

Inference:

from tinfoil import TinfoilAI

client = TinfoilAI(
    enclave="whisper-large-v3-turbo.model.tinfoil.sh",
    repo="tinfoilsh/confidential-whisper-large-v3",
    api_key="YOUR_API_KEY",
)

# Open audio file
with open("audio.mp3", "rb") as audio_file:
    transcription = client.audio.transcriptions.create(
        model="whisper-large-v3-turbo",
        file=audio_file,
    )
    
print(transcription.text)