Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Yue Chinese
whisper
whisper-event
Generated from Trainer
Eval Results (legacy)
Instructions to use Scrya/whisper-large-v2-cantonese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Scrya/whisper-large-v2-cantonese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Scrya/whisper-large-v2-cantonese")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("Scrya/whisper-large-v2-cantonese") model = AutoModelForSpeechSeq2Seq.from_pretrained("Scrya/whisper-large-v2-cantonese") - Notebooks
- Google Colab
- Kaggle
Each sentence is way too long
#2
by sdugoten - opened
I converted the model and use whisper faster to do the export. There is one issue, the length of each sentence is way too long for use as subtitles as you see in the screenshot above using your model.
Using regular large-v2 model don't have this issue, as you can see the export from the original large-v2 below

