Instructions to use facebook/textless_sm_et_en with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Fairseq
How to use facebook/textless_sm_et_en with Fairseq:
from fairseq.checkpoint_utils import load_model_ensemble_and_task_from_hf_hub models, cfg, task = load_model_ensemble_and_task_from_hf_hub( "facebook/textless_sm_et_en" ) - Notebooks
- Google Colab
- Kaggle
File size: 306 Bytes
bcc8ba1 93b1356 bcc8ba1 93b1356 | 1 2 3 4 5 6 7 8 9 10 11 12 13 | ---
library_name: fairseq
task: audio-to-audio
tags:
- fairseq
- audio
- audio-to-audio
- speech-to-speech-translation
license: cc-by-nc-4.0
---
You can try out the model on the right of the page by uploading or recording.
For model usage, please refer to https://huggingface.co/facebook/textless_sm_cs_en
|