Instructions to use qmeeus/whisper-large-multilingual-spoken-ner-pipeline-step-1 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use qmeeus/whisper-large-multilingual-spoken-ner-pipeline-step-1 with Transformers:
# Load model directly from transformers import WhisperSLU model = WhisperSLU.from_pretrained("qmeeus/whisper-large-multilingual-spoken-ner-pipeline-step-1", dtype="auto") - Notebooks
- Google Colab
- Kaggle
whisper-large-multilingual-spoken-ner-pipeline-step-1 / checkpoint-2000 /model-00002-of-00002.safetensors
- Xet hash:
- 05c4ddd285eb0bc149d6980e4764686707f5ec50a4ffee05a342b41d3f0e50a1
- Size of remote file:
- 1.23 GB
- SHA256:
- 64914df534a91786688ebbb186e4f91c9a1edf470eb8846f2ef7fce48a8176ba
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.