Feature Extraction
Transformers
PyTorch
English
distilled_speech
speech
audio
data2vec
distillation
custom_code
Instructions to use TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("feature-extraction", model="TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad", trust_remote_code=True)# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad", trust_remote_code=True, device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download preprocessor_config.json from TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad: direct link, hf CLI and curl.
- Browser
- Download file 166 Bytes
-
https://huggingface.co/TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad/resolve/refs%2Fpr%2F2/preprocessor_config.json
- Command line
-
hf download hf://TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad@refs/pr/2/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/TuKoResearch/AuriStreamDistillLarge_100M40PredTeacher_bad/resolve/refs%2Fpr%2F2/preprocessor_config.json
166 Bytes
| { | |
| "feature_extractor_type": "Wav2Vec2FeatureExtractor", | |
| "sampling_rate": 16000, | |
| "do_normalize": true, | |
| "padding_value": 0.0, | |
| "return_attention_mask": false | |
| } |