Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
English
hubert
speech
audio
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use facebook/hubert-large-ls960-ft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/hubert-large-ls960-ft with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/hubert-large-ls960-ft")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("facebook/hubert-large-ls960-ft") model = AutoModelForCTC.from_pretrained("facebook/hubert-large-ls960-ft") - Notebooks
- Google Colab
- Kaggle
GGUF + pure-C++ runtime in CrispASR (HuBERT on the wav2vec2 backend)
#6 opened 23 days ago
by
cstr
Add Open ASR Leaderboard evaluation results
#5 opened about 2 months ago
by
SaylorTwift
Adding `safetensors` variant of this model
#4 opened about 1 year ago
by
SFconvertbot
When executing Wav2Vec2Processor.from_pretrained("facebook/hubert-large-ls960-ft"), a warning appears: "Ignored unknown kwarg option 'normalize'".
๐ 1
1
#3 opened over 1 year ago
by
lifeplayer
How to get embeddings using hubert model
3
#2 opened over 2 years ago
by
pulkitmehtawork
Adding `safetensors` variant of this model
๐ 3
#1 opened about 3 years ago
by
SFconvertbot