Automatic Speech Recognition
Transformers
PyTorch
French
wav2vec2
Generated from Trainer
hf-asr-leaderboard
mozilla-foundation/common_voice_8_0
robust-speech-event
Eval Results (legacy)
Instructions to use AlexN/xls-r-300m-fr with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use AlexN/xls-r-300m-fr with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="AlexN/xls-r-300m-fr")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("AlexN/xls-r-300m-fr") model = AutoModelForCTC.from_pretrained("AlexN/xls-r-300m-fr", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download validate.sh from AlexN/xls-r-300m-fr: direct link, hf CLI and curl.
- Browser
- Download file 303 Bytes
-
https://huggingface.co/AlexN/xls-r-300m-fr/resolve/main/validate.sh
- Command line
-
hf download hf://AlexN/xls-r-300m-fr/validate.sh
-
curl -L -o validate.sh https://huggingface.co/AlexN/xls-r-300m-fr/resolve/main/validate.sh
303 Bytes
| python eval.py --model_id="./" --dataset="mozilla-foundation/common_voice_8_0" --config="fr" --split="test" --log_outputs | |
| python eval.py --model_id="./" --dataset="speech-recognition-community-v2/dev_data" --config="fr" \ | |
| --split="validation" --chunk_length_s="5.0" --stride_length_s="1.0" --log_outputs |