Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
ONNX
Safetensors
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLab/nb-whisper-base-beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLab/nb-whisper-base-beta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLab/nb-whisper-base-beta")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLab/nb-whisper-base-beta") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLab/nb-whisper-base-beta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "test_fleurs": { | |
| "cer": 4.49824700668122, | |
| "exact_cer": 5.7367488876409345, | |
| "exact_wer": 15.324295587453483, | |
| "wer": 10.958005249343831 | |
| }, | |
| "test_stortinget": { | |
| "cer": 8.517932301008267, | |
| "exact_cer": 9.14528055676381, | |
| "exact_wer": 16.659123680415952, | |
| "wer": 12.97694669976021 | |
| } | |
| } |