Instructions to use anzorq/w2v-bert-2.0-kbd with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use anzorq/w2v-bert-2.0-kbd with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="anzorq/w2v-bert-2.0-kbd")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("anzorq/w2v-bert-2.0-kbd") model = AutoModelForCTC.from_pretrained("anzorq/w2v-bert-2.0-kbd", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from anzorq/w2v-bert-2.0-kbd: direct link, hf CLI and curl.
- Browser
- Download file 4.92 kB
-
https://huggingface.co/anzorq/w2v-bert-2.0-kbd/resolve/main/training_args.bin
- Command line
-
hf download hf://anzorq/w2v-bert-2.0-kbd/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/anzorq/w2v-bert-2.0-kbd/resolve/main/training_args.bin
4.92 kB
- Xet hash:
- dd6831358f674af3877f8cc8d7a29f68795702d1788a47a908aa76bd43d57fe9
- Size of remote file:
- 4.92 kB
- SHA256:
- 6aeafed71f361f77ed77608396c8924d1a3402009a1daf25e5546d711d2f0d96
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.