Instructions to use esb/wav2vec2-aed-pretrained with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use esb/wav2vec2-aed-pretrained with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="esb/wav2vec2-aed-pretrained")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("esb/wav2vec2-aed-pretrained") model = AutoModelForSpeechSeq2Seq.from_pretrained("esb/wav2vec2-aed-pretrained", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download flax_model.msgpack from esb/wav2vec2-aed-pretrained: direct link, hf CLI and curl.
- Browser
- Download file 2.35 GB
-
https://huggingface.co/esb/wav2vec2-aed-pretrained/resolve/main/flax_model.msgpack
- Command line
-
hf download hf://esb/wav2vec2-aed-pretrained/flax_model.msgpack
-
curl -L -o flax_model.msgpack https://huggingface.co/esb/wav2vec2-aed-pretrained/resolve/main/flax_model.msgpack
2.35 GB
- Xet hash:
- b06f010b6eea4f6630bd3c92312af8cb92f081ffe6250ae4eef097e37f891ffd
- Size of remote file:
- 2.35 GB
- SHA256:
- 426a0c8b8f095282de9d9080d52d8d2bf0df5ff4d549023dc9583079af514fd7
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.