Automatic Speech Recognition
Transformers
PyTorch
JAX
Portuguese
wav2vec2
audio
speech
apache-2.0
portuguese-speech-corpus
PyTorch
voxpopuli
Eval Results (legacy)
Instructions to use joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt") model = AutoModelForCTC.from_pretrained("joaoalvarenga/wav2vec2-large-100k-voxpopuli-pt") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 51aa4b7e095bdac0b434f66f1d8b89fbd088b654808c1e1e81052ae264346bd0
- Size of remote file:
- 1.26 GB
- SHA256:
- cfc46c71bc617388fbb6f37d062767a628204630e9f8a274f0b0519511da9d60
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.