nvidia/parakeet-rnnt-1.1b 🖼️ → 📝

▶️ 18.2K runs 📅 Jan 2024 ⚙️ Cog 0.8.6 🔗 GitHub 📄 Paper ⚖️ License

asr speech-to-text

About

🗣️ Nvidia + Suno.ai's speech-to-text conversion with high accuracy and efficiency 📝

Example Output

Output

well i don't wish to see it any more observed phoebe turning away her eyes it is certainly very like the old portrait

Performance Metrics

1.43s Prediction Time

100.03s Total Time

Input Parameters

audio_file (required) Type: string: Input audio file to be transcribed by the ASR model

Output Schema

Output

Type: string

Example Execution Logs

[!] Audio file /tmp/tmp5b0ke4ee2086-149220-0033.wav is mono: True
[!] Audio file /tmp/tmp5b0ke4ee2086-149220-0033.wav is already mono
Transcribing:   0%|          | 0/1 [00:00<?, ?it/s]
Transcribing: 100%|██████████| 1/1 [00:00<00:00,  1.23it/s]
Transcribing: 100%|██████████| 1/1 [00:00<00:00,  1.23it/s]

Version Details

Version ID: 73ddbebaef172a47c8dfdd79381f110bfdc7691bcc7a4edde82f0a39e380ce50
Version Created: January 4, 2024

Run on Replicate →