Automatic Speech Recognition
Transformers
PyTorch
speech-encoder-decoder
speech
xls_r
xls_r_translation
Instructions to use facebook/wav2vec2-xls-r-2b-22-to-16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/wav2vec2-xls-r-2b-22-to-16 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="facebook/wav2vec2-xls-r-2b-22-to-16")# Load model directly from transformers import AutoTokenizer, AutoModelForSpeechSeq2Seq tokenizer = AutoTokenizer.from_pretrained("facebook/wav2vec2-xls-r-2b-22-to-16") model = AutoModelForSpeechSeq2Seq.from_pretrained("facebook/wav2vec2-xls-r-2b-22-to-16", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0, | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |