Instructions to use dmusingu/luganda_wav2vec2_ctc_reg with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use dmusingu/luganda_wav2vec2_ctc_reg with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="dmusingu/luganda_wav2vec2_ctc_reg")# pip install -U transformers accelerate # Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("dmusingu/luganda_wav2vec2_ctc_reg") model = AutoModelForCTC.from_pretrained("dmusingu/luganda_wav2vec2_ctc_reg", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tmp-checkpoint-2000/preprocessor_config.json from dmusingu/luganda_wav2vec2_ctc_reg: direct link, hf CLI and curl.
- Browser
- Download file 215 Bytes
-
https://huggingface.co/dmusingu/luganda_wav2vec2_ctc_reg/resolve/main/tmp-checkpoint-2000/preprocessor_config.json
- Command line
-
hf download hf://dmusingu/luganda_wav2vec2_ctc_reg/tmp-checkpoint-2000/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/dmusingu/luganda_wav2vec2_ctc_reg/resolve/main/tmp-checkpoint-2000/preprocessor_config.json
215 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000 | |
| } | |