subformer/meta-omnilingual-asr-1b 🖼️❓ → 📝

▶️ 14 runs 📅 Nov 2025 ⚙️ Cog 0.16.7 🔗 GitHub 📄 Paper ⚖️ License
multilingual-asr speech-to-text

About

Omnilingual ASR 1B by Meta (Unofficial) - Automatic speech recognition supporting 1,693 languages with balanced accuracy and speed. Best general-purpose choice for professional transcription services.

Example Output

Output

this is the micromachine man presenting the most midget miniature modicate of micromachine each one has dramatic details terrific trent precision paint jobs plus incredible micromachine pocket playsets there's a police station fire station restaurant service station and more perfect pocket portables to take any place and there are many miniature playsets to play with it each one comes with its own special ludition micromachine vehicle and fun fantastic features that miraculously move raise the boat lift at the airport marina man in the gun turret at the army base clean your car at the carwash raise the tolbridge and these playsets fit together to form a micromachine world micromachine pocket playsets are tremendously tiny so perfectly precise so dazzlingly detailed your on a pocket them all micromachines and micromachine pocket playsets sold separately from galoob the smaller they are the better they are

Performance Metrics

31.78s Prediction Time
239.17s Total Time
All Input Parameters
{
  "audio": "https://replicate.delivery/pbxt/O8WFNEILcLBkeiXoqcnlmY2d2vvF8juAhQYXSu1g7C0wCyB7/micro-machines.wav",
  "language": "eng_Latn"
}
Input Parameters
audio (required) Type: string
Audio file to transcribe. Supports most audio formats (MP3, WAV, FLAC, etc). Maximum 40 seconds.
language Default: auto
Select language for transcription. Choose 'auto' for automatic language detection, or select a specific language code.
Output Schema

Output

Type: string

Example Execution Logs
2025-11-27 18:35:20 - INFO - ============================================================
2025-11-27 18:35:20 - INFO - Starting new transcription request
2025-11-27 18:35:20 - INFO - ============================================================
2025-11-27 18:35:20 - INFO - Input parameters:
2025-11-27 18:35:20 - INFO -   - Audio file: /tmp/tmpsd3kf9ycmicro-machines.wav
2025-11-27 18:35:20 - INFO -   - Language: eng_Latn
2025-11-27 18:35:20 - INFO - Audio file found - Size: 5148.82 KB
2025-11-27 18:35:20 - INFO - Converting audio to WAV format...
2025-11-27 18:35:20 - INFO - Audio duration: 29.89 seconds
2025-11-27 18:35:20 - INFO - Audio converted to WAV: /tmp/tmp7_weh5l0.wav (sample rate: 44100 Hz)
2025-11-27 18:35:20 - INFO - Using specified language: eng_Latn
2025-11-27 18:35:20 - INFO - Starting transcription...
2025-11-27 18:35:52 - INFO - Transcription completed in 31.48 seconds
2025-11-27 18:35:52 - INFO - Transcription result length: 917 characters
2025-11-27 18:35:52 - INFO - Preview: this is the micromachine man presenting the most midget miniature modicate of micromachine each one ...
2025-11-27 18:35:52 - INFO - ============================================================
2025-11-27 18:35:52 - INFO - Transcription request completed successfully
2025-11-27 18:35:52 - INFO - ============================================================
2025-11-27 18:35:52 - INFO - Cleaned up temporary file: /tmp/tmp7_weh5l0.wav
Version Details
Version ID
de359b7e0ee3f4fd947c15ebce80d66f237a649f5a18c9ab6d02d691aff1e625
Version Created
November 27, 2025
Run on Replicate →