Automatic Speech Recognition
Transformers
PyTorch
TensorBoard
Portuguese
wav2vec2
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_7_0
robust-speech-event
Eval Results (legacy)
Instructions to use lgris/wav2vec2-xls-r-pt-cv7-from-bp400h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use lgris/wav2vec2-xls-r-pt-cv7-from-bp400h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="lgris/wav2vec2-xls-r-pt-cv7-from-bp400h")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("lgris/wav2vec2-xls-r-pt-cv7-from-bp400h") model = AutoModelForCTC.from_pretrained("lgris/wav2vec2-xls-r-pt-cv7-from-bp400h", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| python3 eval.py --model_id ./ --dataset mozilla-foundation/common_voice_7_0 --config pt --split test --log_outputs | |
| python3 eval.py --stride_length_s 1.0 --chunk_length_s 5.0 --model_id ./ --dataset speech-recognition-community-v2/dev_data --config pt --split validation --log_outputs | |