Automatic Speech Recognition
Transformers
PyTorch
Portuguese
wav2vec2
mozilla-foundation/common_voice_7_0
hf-asr-leaderboard
Eval Results (legacy)
Instructions to use lgris/bp_400h_xlsr2_300M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lgris/bp_400h_xlsr2_300M with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lgris/bp_400h_xlsr2_300M")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lgris/bp_400h_xlsr2_300M") model = AutoModelForCTC.from_pretrained("lgris/bp_400h_xlsr2_300M") - Notebooks
- Google Colab
- Kaggle
- Downloads last month
- 12
Space using lgris/bp_400h_xlsr2_300M 1
Evaluation results
- Test WER on Common Voice 7self-reported10.830
- Test CER on Common Voice 7self-reported3.110
- Test WER on Robust Speech Event - Dev Dataself-reported22.480
- Test CER on Robust Speech Event - Dev Dataself-reported9.330