Instructions to use nyralabs/CrisperWhisper with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nyralabs/CrisperWhisper with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nyralabs/CrisperWhisper")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nyralabs/CrisperWhisper") model = AutoModelForSpeechSeq2Seq.from_pretrained("nyralabs/CrisperWhisper") - Notebooks
- Google Colab
- Kaggle
Only works with English and German with the FasterWhisper version
#16
by David526sky - opened
I lot a lot of time with this model to discover at the end that it only works with English and German. It is a real shame that no information about this is given.
The version with transformers is not working.
Only the version with faster whisper worked.
Do not loose your time trying to install it. The Linux Software Speech Note 4.8.0 Beta version (in Flathub) has integrated this model for English and German, test it there.
David526sky changed discussion title from Impossible to make work via Docker or via the transformer installation to Only works with English and German with the FasterWhisper version