Automatic Speech Recognition
Transformers
PyTorch
TensorFlow
English
German
speech_to_text
audio
speech-translation
Instructions to use facebook/s2t-small-covost2-en-de-st with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/s2t-small-covost2-en-de-st with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/s2t-small-covost2-en-de-st")# Load model directly from transformers import AutoProcessor, AutoModelForSpeechSeq2Seq processor = AutoProcessor.from_pretrained("facebook/s2t-small-covost2-en-de-st") model = AutoModelForSpeechSeq2Seq.from_pretrained("facebook/s2t-small-covost2-en-de-st", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Xet hash:
- a07e90957a419e226e333563cc496dd6b2887afa68ae9c19f0e547bfcec9739f
- Size of remote file:
- 108 MB
- SHA256:
- e4774863bc064dd61b7b806f73405ea479210f964444e1b5f4dc459c8a682ec3
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.