Originally published at: Open ASR Leaderboard - a Hugging Face Space by hf-audio
Top‑ranked on the HuggingFace Open‑ASR leaderboard, the hybrid LLM + ASR model is open‑source and production‑ready.
jwitsoe
1
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Deploying NVIDIA Riva Multilingual ASR with Whisper and Canary Architectures While Selectively Deactivating NMT | 1 | 37 | February 20, 2025 | |
| NVIDIA Speech AI Models Deliver Industry-Leading Accuracy and Performance | 1 | 17 | June 4, 2025 | |
| 업계 최고의 정확도와 성능을 제공하는 NVIDIA 음성 AI 모델 | 1 | 9 | June 9, 2025 | |
| GPU-Accelerated Speech to Text with Kaldi: A Tutorial on Getting Started | 7 | 846 | March 6, 2021 | |
| New Standard for Speech Recognition and Translation from the NVIDIA NeMo Canary Model | 2 | 289 | August 8, 2024 | |
| NVIDIA Speech and Translation AI Models Set Records for Speed and Accuracy | 1 | 243 | March 19, 2024 | |
| Accelerating Leaderboard-Topping ASR Models 10x with NVIDIA NeMo | 1 | 37 | September 24, 2024 | |
| Trainable version of Parakeet-CTC-XXL-1.1B ASR Multilingual with Universal Tokenizer | 0 | 36 | April 9, 2025 | |
| ASR with streaming inference and diarization | 1 | 89 | October 1, 2024 | |
| List ASR models support by nemo2riva conversion | 5 | 108 | May 14, 2025 |