aqasemi/whisper-jax 🖼️ → ❓

▶️ 122.5K runs 📅 Jul 2023 ⚙️ Cog 0.8.3
language-detection speech-to-text

About

Faster and cheaper Whisper-AI Large-v2 responses. JAX implementation of OpenAI's Whisper model for up to 15x speed-up (doesn't support TPU).

Example Output

Output

{"transcription":" My name is King Canute and I have come to kill you for the crimes your father committed against my people. Well I hate to disappoint you.","detected_language":"Detected language 'en' with probability 0.979980"}

Performance Metrics

2.71s Prediction Time
2.90s Total Time
Input Parameters
audio (required) Type: string
Audio file
Output Schema

Output

Example Execution Logs
Transcribe with large-v2 model
Version Details
Version ID
fb09fe931a654f989fffaabdf46b7b5c69f8ace6b89555d84eae6173d49724f1
Version Created
July 28, 2023
Run on Replicate →