Automatic Speech Recognition
Transformers
PyTorch
JAX
Catalan
wav2vec2
audio
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use PereLluis13/Wav2Vec2-Large-XLSR-53-catalan with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PereLluis13/Wav2Vec2-Large-XLSR-53-catalan with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="PereLluis13/Wav2Vec2-Large-XLSR-53-catalan")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("PereLluis13/Wav2Vec2-Large-XLSR-53-catalan") model = AutoModelForCTC.from_pretrained("PereLluis13/Wav2Vec2-Large-XLSR-53-catalan", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- e24d60c99c5e4af5ae8aeff352c729805901ee3c3b47c47bce65ae08540f6f38
- Size of remote file:
- 1.26 GB
- SHA256:
- b660c40611ede5c5645dcc0345bc144b66eb747e020fd7fab199f1268114c98f
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.