Instructions to use facebook/wav2vec2-large-960h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/wav2vec2-large-960h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-large-960h")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("facebook/wav2vec2-large-960h") model = AutoModelForCTC.from_pretrained("facebook/wav2vec2-large-960h") - Notebooks
- Google Colab
- Kaggle
Add Open ASR Leaderboard evaluation results
#7 opened about 1 month ago
by
SaylorTwift
Adding `safetensors` variant of this model
#6 opened 8 months ago
by
SFconvertbot
how to fine-tune to the ultimate performance? I only got 2.9% on test-clean
😔 1
#5 opened 10 months ago
by
wesfggfd
Update README.md
#4 opened over 2 years ago
by
sanchit-gandhi
Adding `safetensors` variant of this model
#3 opened about 3 years ago
by
SFconvertbot
Example code fixed
#2 opened over 3 years ago
by
samyxdev
Wav2vec2 finetuning - Evaluation WER does not change
1
#1 opened almost 4 years ago
by
thardindubph200