Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
JAX
English
wav2vec2
speech
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use facebook/wav2vec2-large-960h-lv60-self with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/wav2vec2-large-960h-lv60-self with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-960h-lv60-self")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("facebook/wav2vec2-large-960h-lv60-self") model = AutoModelForCTC.from_pretrained("facebook/wav2vec2-large-960h-lv60-self") - Notebooks
- Google Colab
- Kaggle
Add Open ASR Leaderboard evaluation results
#9 opened about 2 months ago
by
SaylorTwift
facing issues while using access token of the following model facebook/wav2vec2-large-960h-lv60-self
1
#8 opened about 2 years ago
by
Webster9
Update README.md
#6 opened over 2 years ago
by
sanchit-gandhi
Adding `safetensors` variant of this model
#5 opened about 3 years ago
by
SFconvertbot
Naming of the facebook/wav2vec2 variants
#4 opened over 3 years ago
by
bhaddow
The Output was unpredictable
#3 opened over 3 years ago
by
prashanth07
Fixes evaluation instructions and updates WER scores
6
#2 opened almost 4 years ago
by
andreagasparini
Removes annoying warning: missing "sampling_rate" argument
3
#1 opened almost 4 years ago
by
andreagasparini