Instructions to use KBLab/kb-whisper-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use KBLab/kb-whisper-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="KBLab/kb-whisper-large")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("KBLab/kb-whisper-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("KBLab/kb-whisper-large", device_map="auto") - Notebooks
- Google Colab
- Kaggle
swhisper pipeline combines kb-whisper-large with diarization
#16
by tophee - opened
To whom it may concern: I have created a pipeline that produces verbatim Swedish transcriptions (using whisper-timestamped with kb-whisper-large) and speaker diarization (using pyannote). Still work in progress, but it produces decent results and does a lot of logging to help you tweak the settings if needed: https://github.com/papatistos/swhisper