Automatic Speech Recognition
Transformers
PyTorch
Portuguese
wav2vec2
audio
speech
portuguese-speech-corpus
PyTorch
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use lgris/wav2vec2-large-xlsr-open-brazilian-portuguese with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lgris/wav2vec2-large-xlsr-open-brazilian-portuguese with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lgris/wav2vec2-large-xlsr-open-brazilian-portuguese")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lgris/wav2vec2-large-xlsr-open-brazilian-portuguese") model = AutoModelForCTC.from_pretrained("lgris/wav2vec2-large-xlsr-open-brazilian-portuguese", device_map="auto") - Notebooks
- Google Colab
- Kaggle
There are only approximately 168.35 hours rather than 284 hours of Portuguese speech at the Second dataset: MLS?
#2 opened over 2 years ago
by
xiongcai
Adding `safetensors` variant of this model
#1 opened over 3 years ago
by
SFconvertbot