Instructions to use mazkooleg/0-9up-data2vec-audio-base-960h-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mazkooleg/0-9up-data2vec-audio-base-960h-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="mazkooleg/0-9up-data2vec-audio-base-960h-ft")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForAudioClassification tokenizer = AutoTokenizer.from_pretrained("mazkooleg/0-9up-data2vec-audio-base-960h-ft") model = AutoModelForAudioClassification.from_pretrained("mazkooleg/0-9up-data2vec-audio-base-960h-ft", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from mazkooleg/0-9up-data2vec-audio-base-960h-ft: direct link, hf CLI and curl.
- Browser
- Download file 3.5 kB
-
https://huggingface.co/mazkooleg/0-9up-data2vec-audio-base-960h-ft/resolve/main/training_args.bin
- Command line
-
hf download hf://mazkooleg/0-9up-data2vec-audio-base-960h-ft/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/mazkooleg/0-9up-data2vec-audio-base-960h-ft/resolve/main/training_args.bin
3.5 kB
- Xet hash:
- 5b8c408ea82efc20c257f113b25fe526f173651f6ea37760bd3c77543302552b
- Size of remote file:
- 3.5 kB
- SHA256:
- c250b5bca01b8d357a0e1316a980170999de41f8935c6e0ba240d04299dba5fc
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.