Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
TensorBoard
ONNX
Safetensors
whisper
audio
asr
hf-asr-leaderboard
Instructions to use NbAiLabBeta/nb-whisper-small-semantic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use NbAiLabBeta/nb-whisper-small-semantic with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="NbAiLabBeta/nb-whisper-small-semantic")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("NbAiLabBeta/nb-whisper-small-semantic") model = AutoModelForSpeechSeq2Seq.from_pretrained("NbAiLabBeta/nb-whisper-small-semantic") - Notebooks
- Google Colab
- Kaggle
| { | |
| "template_url": "https://raw.githubusercontent.com/NbAiLab/nb-whisper/main/template.md", | |
| "replacements": { | |
| "#Finetuned#": "# Finetuned Semantic model. \n\nThis model is trained 200 additional steps on top of the main model. The output from this model is less verbatim than when using the main model. The style might be more suited for instance for subtitling of videos since the goal is to use as few words as possible to express the essence of what is said.", | |
| "#Size#": "Small", | |
| "#size#": "small", | |
| "#model_name#": "NbAiLabBeta/nb-whisper-small-semantic" | |
| } | |
| } | |