Automatic Speech Recognition
Transformers
PyTorch
English
data2vec-audio
speech
hf-asr-leaderboard
Eval Results (legacy)
Eval Results
Instructions to use facebook/data2vec-audio-base-960h with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/data2vec-audio-base-960h with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/data2vec-audio-base-960h")# Load model directly from transformers import AutoTokenizer, AutoModelForCTC tokenizer = AutoTokenizer.from_pretrained("facebook/data2vec-audio-base-960h") model = AutoModelForCTC.from_pretrained("facebook/data2vec-audio-base-960h") - Notebooks
- Google Colab
- Kaggle
Transcribe Streaming audio and very long audio files(Out of Memory:how to read in chunks)
#1
by mazharsaif - opened
are there any methods to read long audio files in chunks to avoid out of memory errors, and also transcribe streaming audio