Instructions to use kehanlu/mandarin-wav2vec2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use kehanlu/mandarin-wav2vec2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="kehanlu/mandarin-wav2vec2")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModel processor = AutoProcessor.from_pretrained("kehanlu/mandarin-wav2vec2") model = AutoModel.from_pretrained("kehanlu/mandarin-wav2vec2", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from kehanlu/mandarin-wav2vec2: direct link, hf CLI and curl.
- Browser
- Download file 378 MB
-
https://huggingface.co/kehanlu/mandarin-wav2vec2/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://kehanlu/mandarin-wav2vec2/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/kehanlu/mandarin-wav2vec2/resolve/main/pytorch_model.bin
378 MB
- Xet hash:
- cf809cb47cc2870ea82b6442dbcdc7164490eb203c8a4438d321c4fb0c2f0254
- Size of remote file:
- 378 MB
- SHA256:
- 9377766bf9752f49a4114ff766368e89b562b1d1d74c91bb99d9a658ea198429
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.