Automatic Speech Recognition
Transformers
PyTorch
Portuguese
wav2vec2
audio
speech
portuguese-speech-corpus
PyTorch
Eval Results (legacy)
# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("alefiury/wav2vec2-large-xlsr-53-coraa-brazilian-portuguese-gain-normalization-sna")
model = AutoModelForCTC.from_pretrained("alefiury/wav2vec2-large-xlsr-53-coraa-brazilian-portuguese-gain-normalization-sna")Quick Links
Wav2vec 2.0 trained with CORAA Portuguese Dataset and Open Portuguese Datasets
This a the demonstration of a fine-tuned Wav2vec model for Portuguese using the following datasets:
Repository
The repository that implements the model to be trained and tested is avaible here.
- Downloads last month
- 42
Dataset used to train alefiury/wav2vec2-large-xlsr-53-coraa-brazilian-portuguese-gain-normalization-sna
Evaluation results
- Test CORAA WERself-reported24.89%
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="alefiury/wav2vec2-large-xlsr-53-coraa-brazilian-portuguese-gain-normalization-sna")