Automatic Speech Recognition
Transformers
PyTorch
JAX
French
wav2vec2
audio
hf-asr-leaderboard
mozilla-foundation/common_voice_6_0
robust-speech-event
speech
xlsr-fine-tuning-week
Eval Results (legacy)
Instructions to use bonvent/test2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use bonvent/test2 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="bonvent/test2")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("bonvent/test2") model = AutoModelForCTC.from_pretrained("bonvent/test2") - Notebooks
- Google Colab
- Kaggle
| # CV - TEST | |
| python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-french --dataset mozilla-foundation/common_voice_6_0 --config fr --split test --log_outputs --greedy | |
| mv log_mozilla-foundation_common_voice_6_0_fr_test_predictions.txt log_mozilla-foundation_common_voice_6_0_fr_test_predictions_greedy.txt | |
| mv mozilla-foundation_common_voice_6_0_fr_test_eval_results.txt mozilla-foundation_common_voice_6_0_fr_test_eval_results_greedy.txt | |
| python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-french --dataset mozilla-foundation/common_voice_6_0 --config fr --split test --log_outputs | |
| # HF EVENT - DEV | |
| python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-french --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0 --log_outputs --greedy | |
| mv log_speech-recognition-community-v2_dev_data_fr_validation_predictions.txt log_speech-recognition-community-v2_dev_data_fr_validation_predictions_greedy.txt | |
| mv speech-recognition-community-v2_dev_data_fr_validation_eval_results.txt speech-recognition-community-v2_dev_data_fr_validation_eval_results_greedy.txt | |
| python eval.py --model_id jonatasgrosman/wav2vec2-large-xlsr-53-french --dataset speech-recognition-community-v2/dev_data --config fr --split validation --chunk_length_s 5.0 --stride_length_s 1.0 --log_outputs | |