Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Safetensors
wav2vec2
Generated from Trainer
Eval Results (legacy)
Instructions to use Shehryar718/URDU-ASR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Shehryar718/URDU-ASR with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="Shehryar718/URDU-ASR")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("Shehryar718/URDU-ASR") model = AutoModelForCTC.from_pretrained("Shehryar718/URDU-ASR", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from Shehryar718/URDU-ASR: direct link, hf CLI and curl.
- Browser
- Download file 1.26 GB
-
https://huggingface.co/Shehryar718/URDU-ASR/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://Shehryar718/URDU-ASR/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/Shehryar718/URDU-ASR/resolve/main/pytorch_model.bin
1.26 GB
- Xet hash:
- eeb132a45ee7733f86a525bd84c81bd311e1a72f74b94c137e3af7a188d3e3a3
- Size of remote file:
- 1.26 GB
- SHA256:
- 1ad592d0ded82d92465a242724d374cc3280007ee08440e710b04c8aeb81ea5e
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.