Automatic Speech Recognition
Transformers
PyTorch
JAX
Safetensors
English
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 jonatasgrosman/wav2vec2-large-xlsr-53-english with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jonatasgrosman/wav2vec2-large-xlsr-53-english with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="jonatasgrosman/wav2vec2-large-xlsr-53-english")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-english") model = AutoModelForCTC.from_pretrained("jonatasgrosman/wav2vec2-large-xlsr-53-english", device_map="auto") - Notebooks
- Google Colab
- Kaggle
what is the length of the audio that the model accepts for training and prediction?
#8
by andromeda01111 - opened
I wanted to train the model on my custom dataset. So i wanted to know the exact audio length that the model accepts for training and prediction. does the model crops the audio we provide?