Automatic Speech Recognition
speechbrain
PyTorch
Kinyarwanda
wav2vec2
CTC
Attention
Transformer
hf-asr-leaderboard
Instructions to use speechbrain/asr-wav2vec2-commonvoice-rw with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- speechbrain
How to use speechbrain/asr-wav2vec2-commonvoice-rw with speechbrain:
from speechbrain.pretrained import EncoderDecoderASR model = EncoderDecoderASR.from_hparams( "speechbrain/asr-wav2vec2-commonvoice-rw" ) model.transcribe_file("file.wav") - 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 | |
| } | |