Instructions to use nccratliri/whisper-large with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use nccratliri/whisper-large with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="nccratliri/whisper-large")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("nccratliri/whisper-large") model = AutoModelForSpeechSeq2Seq.from_pretrained("nccratliri/whisper-large") - Notebooks
- Google Colab
- Kaggle
A clone of the openai/whisper-large.
In this version, the tokenizer's vocabulary does not contain predefined timestamps, which allows more flexible customization.
- Downloads last month
- 7