Whisper Deployment Guide

POST "<YOUR_PRIVATE_WHISPER_DEPLOYMENT>/predict"

headers = {"Authorization": "Bearer YOUR_JWT_TOKEN"}

import requests
import base64
import json

# Read and encode audio file
with open("audio_file.mp3", "rb") as f:
    audio_data = f.read()
    audio_base64 = base64.b64encode(audio_data).decode("utf-8")

# API request with base64
headers = {"Authorization": "Bearer YOUR_JWT_TOKEN"}
payload = {
    "audio_file": audio_base64,                    # Base64-encoded audio data
    "language": "hi",                              # Hindi audio
    "task": "translate",                           # Translate to English
    "vad_model": "silero",                         # Use Silero VAD
    "word_timestamps": True,                       # Include word timestamps
    "without_timestamps": False,                   # Keep timestamps in text
    "diarization": True,                          # Identify speakers
    "vad_onset": 0.5,                             # Speech detection threshold
    "vad_offset": 0.3,                            # Speech end threshold
    "strict_hallucination_reduction": True         # Reduce false content
}

response = requests.post(
    "<YOUR_PRIVATE_WHISPER_DEPLOYMENT>/predict",
    json=payload,
    headers=headers
)

import requests
import json

# API request with URL
headers = {"Authorization": "Bearer YOUR_JWT_TOKEN"}
payload = {
    "audio_file": "https://example.com/audio.mp3", # Publicly accessible audio URL
    "language": "en",                              # English audio
    "task": "transcribe",                          # Transcribe in same language
    "vad_model": "silero",                         # Use Silero VAD
    "word_timestamps": True,                       # Include word timestamps
    "without_timestamps": False,                   # Keep timestamps in text
    "diarization": False,                         # Single speaker
    "vad_onset": 0.5,                             # Speech detection threshold
    "vad_offset": 0.3,                            # Speech end threshold
    "strict_hallucination_reduction": True         # Reduce false content
}

response = requests.post(
    "<YOUR_PRIVATE_WHISPER_DEPLOYMENT>/predict",
    json=payload,
    headers=headers
)

{
    "duration": [
        3.02
    ],
    "transcription": [
        {
            "text": "Hello World",
            "start": 0.0,
            "end": 3.02
        }
    ],
    "word_timestamps": [
        {
            "word": " Hello",
            "start": 0.0,
            "end": 0.34,
            "probability": 0.92
        },
        {
            "word": " World",
            "start": 0.34,
            "end": 0.6,
            "probability": 0.92
        }
    ],
    "diarization": [
        {
            "start": 0.0,
            "end": 0.34,
            "text": "Hello World",
            "speaker": 1
        }
    ],
    "info": {
        "language": "en",
        "probability": 1
    },
    "metrics": {
        "audio_loading_preprocessing": 0.009385824203491211,
        "audio_chunk": 0.014404058456420898,
        "audio_prediction": 0.08741092681884766,
        "audio_word_processing": 0.07052230834960938,
        "audio_diarization": 0.07052850723266602,
        "hallucination_reduction": 0.0004951953887939453
    }
}

{
  "error": "Invalid or expired authentication token",
  "code": "401"
} 

{
  "error": "Internal server error",
  "code": "500"
}