Instructions to use KBLab/kb-whisper-medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KBLab/kb-whisper-medium with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="KBLab/kb-whisper-medium")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("KBLab/kb-whisper-medium") model = AutoModelForSpeechSeq2Seq.from_pretrained("KBLab/kb-whisper-medium", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K
- 1.83 GB xet
- 443 MB xet
- 914 MB xet
- 671 MB xet
- 1.83 GB xet
- 444 MB xet
- 915 MB xet
- 673 MB xet
- 469 MB xet
- 336 MB xet
- 673 MB xet
- 673 MB xet
- 468 MB xet
- 335 MB xet
- 671 MB xet
- 671 MB xet
- 1.63 GB xet
- 415 MB xet
- 813 MB xet
- 621 MB xet
- 437 MB xet
- 307 MB xet
- 621 MB xet
- 621 MB xet
- 1.23 GB xet
- 191 MB xet
- 615 MB xet
- 313 MB xet
- 210 MB xet
- 181 MB xet
- 313 MB xet
- 313 MB xet