Automatic Speech Recognition
NeMo
PyTorch
English
speech
audio
Transducer
TDT
FastConformer
Conformer
NeMo
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use nvidia/parakeet-tdt-0.6b-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- NeMo
How to use nvidia/parakeet-tdt-0.6b-v2 with NeMo:
import nemo.collections.asr as nemo_asr asr_model = nemo_asr.models.ASRModel.from_pretrained("nvidia/parakeet-tdt-0.6b-v2") transcriptions = asr_model.transcribe(["file.wav"]) - Notebooks
- Google Colab
- Kaggle
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: mean_wer | |
| value: 6.05 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: rtfx | |
| value: 3386.02 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: ami_wer | |
| value: 11.16 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: earnings22_wer | |
| value: 11.15 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: gigaspeech_wer | |
| value: 9.74 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: librispeech_clean_wer | |
| value: 1.69 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: librispeech_other_wer | |
| value: 3.19 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: spgispeech_wer | |
| value: 2.17 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: tedlium_wer | |
| value: 3.38 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |
| - dataset: | |
| id: hf-audio/open-asr-leaderboard | |
| task_id: voxpopuli_wer | |
| value: 5.95 | |
| date: '2025-04-15' | |
| source: | |
| url: https://huggingface.co/hf-audio | |
| name: open-asr-leaderboard | |
| user: hf-audio | |