Instructions to use scribe-project/wav2vec2-large-voxrex-300m-radio with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use scribe-project/wav2vec2-large-voxrex-300m-radio with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("automatic-speech-recognition", model="scribe-project/wav2vec2-large-voxrex-300m-radio")# Load model directly from transformers import AutoProcessor, AutoModelForCTC processor = AutoProcessor.from_pretrained("scribe-project/wav2vec2-large-voxrex-300m-radio") model = AutoModelForCTC.from_pretrained("scribe-project/wav2vec2-large-voxrex-300m-radio", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from scribe-project/wav2vec2-large-voxrex-300m-radio: direct link, hf CLI and curl.
- Browser
- Download file 256 Bytes
-
https://huggingface.co/scribe-project/wav2vec2-large-voxrex-300m-radio/resolve/2a783c3a5a676b99b77934bd2f559823c1c3be33/preprocessor_config.json
- Command line
-
hf download hf://scribe-project/wav2vec2-large-voxrex-300m-radio@2a783c3a5a676b99b77934bd2f559823c1c3be33/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/scribe-project/wav2vec2-large-voxrex-300m-radio/resolve/2a783c3a5a676b99b77934bd2f559823c1c3be33/preprocessor_config.json
256 Bytes
| { | |
| "do_normalize": true, | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "feature_size": 1, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "processor_class": "Wav2Vec2Processor", | |
| "return_attention_mask": true, | |
| "sampling_rate": 16000 | |
| } | |