Speech Transcription with parakeet-tdt-0.6b-v2
This demo showcases parakeet-tdt-0.6b-v2, a 600-million-parameter model designed for high-quality English speech recognition.
Key Features:
- Automatic punctuation and capitalization
- Accurate word-level timestamps (click on a segment in the table below to play it!)
- Efficiently transcribes long audio segments (updated to support upto 3 hours) (For even longer audios, see this script)
- Robust performance on spoken numbers, and song lyrics transcription
This model is available for commercial and non-commercial use.
🎙️ Learn more about the Model | 📄 Fast Conformer paper | 📚 TDT paper | 🧑💻 NeMo Repository
Example Audio Files (Click to Load)
Transcription Results (Click row to play segment)
Transcription Segments