Automatic Speech Recognition
Transformers
PyTorch
Safetensors
Chinese
Yue Chinese
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use alvanlii/whisper-small-cantonese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use alvanlii/whisper-small-cantonese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="alvanlii/whisper-small-cantonese")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("alvanlii/whisper-small-cantonese") model = AutoModelForSpeechSeq2Seq.from_pretrained("alvanlii/whisper-small-cantonese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
`use_cache=False`
#11
by jemoka - opened
Hi! Thanks so much for the great model! I wonder why the generation_config for this model doesn't use kv caching? (i.e. use_cache=False); is there a particular reason for this?
Thanks!
hmm, that wasn't intentional. Using cache should be fine
Great, will try it out with the KV cache on.