legacy-datasets/common_voice
Updated โข 1.19k โข 148
How to use BeebekBhz/wav2vec2-large-xlsr-english with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("automatic-speech-recognition", model="BeebekBhz/wav2vec2-large-xlsr-english") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoProcessor, AutoModelForCTC
processor = AutoProcessor.from_pretrained("BeebekBhz/wav2vec2-large-xlsr-english")
model = AutoModelForCTC.from_pretrained("BeebekBhz/wav2vec2-large-xlsr-english", device_map="auto")Fine-tuned facebook/wav2vec2-large-xlsr-53 on English using the train and validation splits of Common Voice 6.1. When using this model, make sure that your speech input is sampled at 16kHz.