Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Instructions to use UrukHan/wav2vec2-russian with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use UrukHan/wav2vec2-russian with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="UrukHan/wav2vec2-russian")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("UrukHan/wav2vec2-russian") model = AutoModelForCTC.from_pretrained("UrukHan/wav2vec2-russian", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- c652e2a8aec75c98335d018a4b7a8f383070d854b185a2f14a83b9a3144e7281
- Size of remote file:
- 3.06 kB
- SHA256:
- b869731b863ca715fcfb96af8228a20276a8f224ae4a1026eee63af92f6b9aa5
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.