Automatic Speech Recognition
Transformers
Safetensors
Persian
wav2vec2
audio
speech
asr
Eval Results (legacy)
Instructions to use lnxdx/Wav2Vec2-Large-XLSR-Persian-ShEMO with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lnxdx/Wav2Vec2-Large-XLSR-Persian-ShEMO with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lnxdx/Wav2Vec2-Large-XLSR-Persian-ShEMO")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lnxdx/Wav2Vec2-Large-XLSR-Persian-ShEMO") model = AutoModelForCTC.from_pretrained("lnxdx/Wav2Vec2-Large-XLSR-Persian-ShEMO", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Ctrl+K