Instructions to use mispeech/ced-mini with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use mispeech/ced-mini with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("audio-classification", model="mispeech/ced-mini", trust_remote_code=True)# Load model directly from transformers import AutoModelForAudioClassification model = AutoModelForAudioClassification.from_pretrained("mispeech/ced-mini", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from mispeech/ced-mini: direct link, hf CLI and curl.
- Browser
- Download file 384 Bytes
-
https://huggingface.co/mispeech/ced-mini/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mispeech/ced-mini/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mispeech/ced-mini/resolve/main/preprocessor_config.json
384 Bytes
| { | |
| "center": true, | |
| "f_max": null, | |
| "f_min": 0, | |
| "feature_extractor_type": "CedFeatureExtractor", | |
| "auto_map": { | |
| "AutoFeatureExtractor": "feature_extraction_ced.CedFeatureExtractor" | |
| }, | |
| "feature_size": 64, | |
| "hop_size": 160, | |
| "n_fft": 512, | |
| "padding_side": "right", | |
| "padding_value": 0.0, | |
| "return_attention_mask": false, | |
| "sampling_rate": 16000, | |
| "win_size": 512 | |
| } | |