nvidia/parakeet

概要

• Nvidia & SunoからparakeetというASRモデルがリリースされた

• FastConformer アーキテクチャをベースにしてRNNT (1.1B, 0.6B), CTC(1.1B, 0.6B)の4モデル

• parakeet-rnnt-1.1b はOpen ASRリーダーボードではOpenAI Whisperを上回る
• FastConformer Transducer1.1B
• The model was trained on 64K hours of English speech collected and prepared by NVIDIA NeMo and Suno teams.
• The training dataset consists of private subset with 40K hours of English speech plus 24K hours from the following public datasets:
• Librispeech 960 hours of English speech
• Fisher Corpus
• Switchboard-1 Dataset
• WSJ-0 and WSJ-1
• National Speech Corpus (Part 1, Part 6)
• VCTK
• VoxPopuli (EN)
• Europarl-ASR (EN)
• Multilingual Librispeech (MLS EN) - 2,000 hour subset
• Mozilla Common Voice (v7.0)
• People's Speech - 12,000 hour subset



• https://huggingface.co/spaces/hf-audio/open_asr_leaderboard

• CC-BY-4.0 ライセンス