Automatic Speech Recognition
Transformers
PyTorch
JAX
TensorBoard
Norwegian
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLabArchive/scream_small_beta with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLabArchive/scream_small_beta with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLabArchive/scream_small_beta")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLabArchive/scream_small_beta") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLabArchive/scream_small_beta", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| from transformers import WhisperForConditionalGeneration | |
| model = WhisperForConditionalGeneration.from_pretrained(".", from_flax=True) | |
| model.save_pretrained(".") | |
| print("\nModel is now converted to PyTorch. There should be a new pytorch_model.bin-file in this directory.") | |