Instructions to use birgermoell/psst-base-rep with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use birgermoell/psst-base-rep with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="birgermoell/psst-base-rep")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("birgermoell/psst-base-rep") model = AutoModelForCTC.from_pretrained("birgermoell/psst-base-rep", device_map="auto") - Notebooks
- Google Colab
- Kaggle
YAML Metadata Warning:empty or missing yaml metadata in repo card
Check out the documentation for more information.
The model is a reproduction of the baseline trained with Wav2vec2-small on PSST
pssteval INFO: ASR metrics for split valid FER: 10.4% PER: 23.1%
- Downloads last month
- 3